Deep learning is an imitation of actual human brain neurons and its functions.

Unlike any other time, the past decade has seen unprecedented development in the field of Artificial Intelligence (AI). There are a lot of talks on machine learning doing things humans currently do in our workplace. Deep learning is leading in some of the fronts of machine learning making practical changes.

Deep learning is an artificial intelligence function that imitates the working of the human brain in processing data and creating patterns for use in decision making. Deep learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural network (ANN). It has networks capable of learning unsupervised or unstructured data. Deep learning is often known as deep neural learning or deep neural network.

Deep learning is often compared with the actual human brain functions. The human brain can recognise a friend’s face or his/her voice even after a long gap. We can find our mother among so many people in a crowded marketplace. The human brain has learned to execute complex day-to-day activities. The functioning system behind the mechanism is 100 billion cells called neurons. The neurons build massive parallel and distributed networks, through which humans learn to carry out complex activities. The deep learning system is an inspiration of a biological neural system. Scientists and researchers started building artificial neural networks so that computers could eventually learn and exhibit intelligence like humans.

There are two types of neural network models used in deep learning,

• Convolutional Neural Network (CNN)- used in image-related applications like autonomous driving and robot vision.
• Recurrent Neural Network (RNN)- used in most of the Natural Language Processing (NLP) based text or voice applications such as chatbots, virtual assistants.

Functions of deep learning

Deep learning brings about an explosion of data in all forms and from across the globe. This large set of data, called big data, is collected from users interface in social media, internet search engines, e-commerce platforms, etc. This enormous data is considered as a data asset when it holds the details of an organisation or a company. Big data can be shared through applications like cloud computing.

Big data is mostly unstructured and contains files from diverse kind of sources like video, images and documents. It is so vast that it could take decades for humans to comprehend it and extract relevant information. Using AI and its applications, organisations make use of the data to increase their revenue and better the working system. Here are some of the use cases of deep learning at work.

Self-driving technology: Self-driving technology is one of the most important prospects that researchers are trying to unravel in the upcoming years. Automotive researchers are using deep learning to automatically detect objects such as stop signs and traffic lights. In order to decrease accidents, deep learning helps detect pedestrians in the road.

Aerospace and defence: Defence needs constant navigation. It will be very good if the navigation system is able to detect safe and unsafe zones from a long distance. Deep learning installed in satellites helps identify objects and locate areas of interest.

Medical Research: Deep learning is a major component in detecting cancer cells. Cancer researchers at UCLA have built an advanced microscope that yields a high-dimensional at a set used to train a deep learning application to accurately identify cancer cells.

Industry automation: Deep learning in industries is used to automatically find unsafe machines and alarms people to get away from the location. It ensures the security of workers in heavily machinery surroundings.

Required tools 

Deep learning mandates a lot of sophisticated tools in which some are free like TensorFlow, PyTorch and Keras. Whereas, some other tools are highly expensive. Data learning deals with enormous data and complex algorithms that needs luxurious hardware infrastructure to handle. The deep learning tools are referred to as Machine Learning as a Service (MLaaS) solutions. Amazon AWS, Microsoft Azure and Google Cloud are some of the platforms that provide deep learning tools.

Advantages of deep learning

• In deep learning, neurons are being trained to perform conceptual tasks such as finding edges in a photo or facial features within the face.
• Deep learning over most of the other machine learning approaches keeps away the worry about trimming down the number of features used.

Disadvantages of deep learning

• Deep learning networks may require hundreds of thousands of millions of hand-labelled examples.
• In deep learning, it is very expensive to train in fast timeframes as fast players need commercial-grade GPUs.

Sometimes deep learning is taken for a ‘black box’ for its complex and extremely difficult to understand the working model.

The post WHAT IS DEEP LEARNING? A SIMPLE GUIDE WITH EXAMPLES appeared first on Artificial Intelligence.

Psychiatrists typically diagnose autism spectrum disorders (ASD) by observing a person’s behavior and by leaning on the Diagnostic and Statistical Manual of Mental Disorders (DSM-5), widely considered the ‘bible’ of mental health diagnosis.

However, there are substantial differences amongst individuals on the spectrum and a great deal remains unknown by science about the causes of autism, or even what autism is. As a result, an accurate diagnosis of ASD and a prognosis prediction for patients can be extremely difficult.

But what if artificial intelligence (AI) could help? Deep learning, a type of AI, deploys artificial neural networks based on the human brain to recognize patterns in a way that is akin to, and in some cases can surpass, human ability. The technique, or rather suite of techniques, has enjoyed remarkable success in recent years in fields as diverse as voice recognition, translation, autonomous vehicles, and drug discovery.

A group of researchers from KAIST in collaboration with the YonseiUniversity College of Medicine has applied these deep learning techniques to autism diagnosis. Their findings were published on August 14 in the journal IEEE Access.

Magnetic resonance imaging (MRI) scans of brains of people known to have autism have been used by researchers and clinicians to try to identify structures of the brain they believed were associated with ASD. These researchers have achieved considerable success in identifying abnormal gray and white matter volume and irregularities in cerebral cortex activation and connections as being associated with the condition.

These findings have subsequently been deployed in studies attempting more consistent diagnoses of patients than has been achieved via psychiatrist observations during counseling sessions. While such studies have reported high levels of diagnostic accuracy, the number of participants in these studies has been small, often under 50, and diagnostic performance drops markedly when applied to large sample sizes or on datasets that include people from a wide variety of populations and locations.

“There was something as to what defines autism that human researchers and clinicians must have been overlooking,” said Keun-Ah Cheon, one of the two corresponding authors and a professor in Department of Child and Adolescent Psychiatry at Severance Hospital of the Yonsei University College of Medicine.

“And humans poring over thousands of MRI scans won’t be able to pick up on what we’ve been missing,” she continued. “But we thought AI might be able to.”

So the team applied five different categories of deep learning models to an open-source dataset of more than 1,000 MRI scans from the Autism Brain Imaging Data Exchange (ABIDE) initiative, which has collected brain imaging data from laboratories around the world, and to a smaller, but higher-resolution MRI image dataset (84 images) taken from the Child Psychiatric Clinic at Severance Hospital, Yonsei University College of Medicine. In both cases, the researchers used both structural MRIs (examining the anatomy of the brain) and functional MRIs (examining brain activity in different regions).

The models allowed the team to explore the structural bases of ASD brain region by brain region, focusing in particular on many structures below the cerebral cortex, including the basal ganglia, which are involved in motor function (movement) as well as learning and memory.

Crucially, these specific types of deep learning models also offered up possible explanations of how the AI had come up with its rationale for these findings.

“Understanding the way that the AI has classified these brain structures and dynamics is extremely important,” said Sang Wan Lee, the other corresponding author and an associate professor at KAIST. “It’s no good if a doctor can tell a patient that the computer says they have autism, but not be able to say why the computer knows that.”

The deep learning models were also able to describe how much a particular aspect contributed to ASD, an analysis tool that can assist psychiatric physicians during the diagnosis process to identify the severity of the autism.

“Doctors should be able to use this to offer a personalized diagnosis for patients, including a prognosis of how the condition could develop,” Lee said.

“Artificial intelligence is not going to put psychiatrists out of a job,” he explained. “But using AI as a tool should enable doctors to better understand and diagnose complex disorders than they could do on their own.”

The post Deep learning helps explore the structural and strategic bases of autism? appeared first on Artificial Intelligence.

Still in lockdown

Week seven of the lockdown and the only immediate future I can think of is “when the heck are we likely to get back to some form of normal life?” Prospects do not look great for anytime soon!

So, I will console myself with thinking further ahead. Actually, when you get to my advanced years thinking too far ahead is maybe not that consoling, but hey ho!

Predicting the future is a bit of a two-edged sword for a control freak like myself – on one hand you will not be around to discover you got it completely wrong, but nor will you be able to wallow in your sweet success if you get some of it right.

The approach most soothsayers appear to take, including Nostradamus – perhaps the most famous of them all, is to be as vague as possible and to write in some obscure French dialect so that translations can be ‘interpreted’ in your favour if so required.

By way of explanation

Most of the things I am most optimistic about are based on my observations regarding the sheer tenacity and ingenuity of humankind. We are where we are because we are the most successful species on earth. Who knows, maybe the most successful species in the universe (though there has to be some doubt about that as we are only really aware of a very, very, very, very, small fraction of one percent of one little bit of it!)

Like all species our success is based upon survival. Survival despite all of the dangers and adversity thrown at us – much of it caused by ourselves it has to be said (think war, pollution, politicians etc).

So, if we are to thrive and continue into the distant future, what do I think we will need to do? Here are a few thoughts (by the way, I hate science fiction with a passion – so think about these things from the science bit only please).

Migration to Other Planets

Sooner or later (probably later, hopefully not too late) this will be inevitable, not least because we are fast ruining the one planet we do currently occupy. Obviously tentative steps have already been made, but perhaps the entire reason for our existence is to eventually populate the universe?

This thought stems from my privately held view that, if you think about it, we are in fact, just another virus like Covid-19, but we have been around longer and more successfully, so have evolved accordingly.

The drive for survival and the stark requirement for more living space will surely mean us looking to colonise the planets in the same way we gradually colonised the world?

How we actually go about doing this will depend upon the outcome of several other of my predictions.

Delay or Reverse the Aging Process

Our lives are currently, just a blink in time compared to the scale of the universe. By the time we gain a little knowledge it is wiped away by death. It is only in the last few centuries that we have been able to pass that knowledge on for future generations, first by word of mouth, then books and now computer networks. But even with this capability, death is still a bit of an ‘inconvenience’ when it comes to being able to make use of the knowledge we gather. Imagine if we could elongate life to the point where 50 years of accumulated knowledge could be followed by, say, another 50 or 100 years of productive application of that knowledge and further research. Imagine if people lived a healthy and productive life of several hundred years?

Sounds a bit scary (and much like my hated science fiction), but just suppose you suggested to someone in the middle ages that the average age of a human would be say 85 years – well surely they would have found that as unbelievable then as a 200 year lifespan seems now?

We already know a great deal about the aging process. It is linked to the deterioration of our natural gene replacement process. And we are now learning how to manipulate genes. Check it out, this is not as far-fetched as it sounds. We have more than doubled the expected lifespan of a human in the western world in the last 10 generations. But again, this is but a blink in time.

Mapping the Human Brain

If you cannot think of any good reason for doing this, you are not using yours very effectively!

 The human brain is one of the most miraculous, complex and intricate entities in our known world. We currently only have the vaguest ideas about exactly how it works to provide us with the memories and cognitive capabilities we all enjoy.

I know this is hard to believe when you have lost your car keys or turned up at Tesco without your purse or wallet, but believe me – you are a wonder, and you brain is the most wonderous part of you!

Apart from the obvious health benefits for dementia etc, imagine if the current research can eventually allow us to identify how the neural network operates then maybe we can begin to replicate this in our computer networks. Imagine the leap this might give us in our collective cognitive and processing capabilities. For one thing it might allow us to process the data we are gathering from the far edges of our galaxy, and beyond, much more effectively and give us a clearer view of exactly what else is out there. Maybe a black hole would not be as black?

Travelling Faster

The size and scale of the universe is mind-boggling. With our current technology the time needed to travel to even the nearest potential ‘new home’ would be, well, astronomical – 40 years to the edge of our solar system, 80,000 years to the nearest star and 749 million years to the nearest galaxy. Even a vastly extended lifespan is not going to cut it!

The only option is to find a way of travelling faster. Ideally a way that does not involve friction, because even though there is a very thin atmosphere in space, it is still sufficient to slow down any propulsion. And where would that propulsion come from? Taking rocket fuel with you is a solution for reaching the moon, but out of the question for extended space travel. Solar power only works if you are ‘near’ to the sun – not feasible when the objective is to get away from the sun. A nuclear-powered spacecraft is way beyond our current technology as it would have to be far too big and heavy to ever launch.

OK so some form of time-travel or molecular disassembly, transmission and reassembly (beam me up Scotty!) are the only options that come to mind right now (pesky science fiction once again) but lets suppose the additional computing power I mentioned in the last paragraph might allow us to identify the secrets that would allow such nonsense?

As a young boy I used to be taken every Saturday morning to our local cinema and watch a space hero called Flash Gordon prance around the screen (no wonder I hate science fiction). I did however marvel at, but entirely dismiss as rubbish, the unbelievably cool device he had which allowed him to see and talk with the evil Emperor Ming on a distant planet.

Yesterday I spoke with and saw my grandkids on a similar device. Mindblowing.

A Single Tribe

The tribal system which pervades all of humanity has served us well up to now. It has helped protect the individual, promote exploration – a breakaway tribe has to wander off to find a new home, and generally support the ‘survival of the fittest’. Strong tribes live, weak tribes die or are assimilated.

However, if we are indeed going to become space travellers, then we will need a single purpose, direction and decision-making system. We need to be Earthlings, not Americans Russians, Australians, or whatever. This would have been considered unthinkable in the past, because the tribal system at its worst has meant we have spent centuries killing each other. But the technology I mentioned above has already started to impact that. Even during this lock-down I have been able to speak from my home in Norwich, UK with people in the USA, Kuala Lumpa, and New Zealand – as if I were in the same room as them. This has got to bode well for a closer cooperation between tribes for the future. Because of such technological advances the world is a much smaller place than it used to be. Probably too small, which brings us back to my first prediction.

So you are probably thinking “what has this to do with Enterprise Big Data”? Well as I tried to explain in my last article, everything has something to do with Big Data. When the astronomers scan the heavens or the medical scientists reviews the results of brain scans they do not immediately get pretty pictures to look at – they get data. It is only when that data is processed and analysed that it begins to make some sort of sense. And that is how observations are made and information is gathered to help resolve the issue in hand.

Big Data Analysis offers the prospect for improving so many aspects of our lives and might just make the difference in the future. If we are to have a future.

The post Science Fiction or Science? How Big Data impacts the future appeared first on Artificial Intelligence.

We all know the feeling: you spot a link to “unbelievably rare historical photos – in color!” or a video of the “cutest puppies in the world!” and you helplessly move your cursor toward it. The site may look a little suspicious, but you’re an amateur historian – or maybe you just really want to see some puppies. Even people who know better often find themselves drawn to dangerous clickbait, and their curiosity sometimes overwhelms their better judgment.

Hackers prey on the elements of our psychology that can be exploited, such as our natural curiosity and our bias toward sensationalism. However, although certain characteristics of the human brain make us susceptible to cyberattacks, we’re also armed with many cognitive defense mechanisms. While these defenses need to be built up over time, the very same features of the brain that can get us into trouble can help us spot and foil cyberattacks.

Many people mistakenly assume that cybersecurity is all about developing more and more sophisticated digital defenses, from stronger encryption to multi-factor authentication. But the vast majority of cyberattacks involve some form of social engineering – the manipulation of human beings to infiltrate a system and steal data. While technological solutions are important, the most powerful cybersecurity tool you have is in your own head.

How Our Brains Can Put Us at Risk

Let’s stay with curiosity for a moment. Consider all the reasons human beings want to learn and discover new things, from the purely functional (such as studying for a test) to the recreational (historical photos and puppy videos). A study published in Neuron cites some of the drivers of curiosity that scholars have identified over the years, including play, exploration, various types of learning, and even neophilia (a fascination with novelty). It’s clear that we’re hardwired to be curious – just spend a few minutes watching a baby who recently learned to crawl.

But the downside is clear: our eagerness to click before we think is one of the main causes of cyberattacks. According to Verizon’s 2019 Data Breach Investigations Report, one-third of data breaches are caused by phishing attacks, which trick employees into sharing sensitive information. These schemes often take the form of “special offers” or other inducements designed to pique our curiosity. Many hackers also hijack devices through unsecured third party apps, which are irresistible to many curious smartphone shoppers.

We’re also hardwired to form habits, both good and bad. As a study in Personality and Social Psychology Review explains, “Bad habits present significant inhibitory challenges.” The study – which defines habits as “implicit associations between contexts and responses that develop through repeated reward learning” – notes that “Drinking too much, eating too much, procrastinating – all can be habitual responses that need to be controlled.” There are a whole lot of bad cybersecurity habits that need to be controlled as well.

For example, how many employees use public WiFi without a VPN, ignore the update prompts they receive on their phones and laptops (which do more than add new features – they ensure your security is up to date), or download third party apps? It’s easy to do all these things because logging onto public WiFi or clicking “remind me later” on vital security updates is a reflex for most people. But here’s the good news: bad habits can be broken.

How Our Brains are Wired for Security

The whole point of cybersecurity training is to take advantage of our cognitive resources to establish healthy habits. One such resource is the capacity for habit formation itself. After the initial process of educating employees on proper cybersecurity practices, their habit-formation mechanisms are at work every time they repeat healthy behaviors. A study in Psychology, Health & Medicine explains this phenomenon: “Results showed that behavior change was initially experienced as cognitively effortful but as automaticity increased, enactment became easier.”

Beyond reversing all the unhealthy behaviors listed above, the cultivation of responsible cybersecurity habits puts security top of mind. This will make employees more circumspect about suspicious emails and links, sharing sensitive information, etc., and it will make them more likely to use resources like password managers and VPNs. At a time when American adults are spending half of every day interacting with media and the number of connected devices is exploding, this generalized cybersecurity awareness is becoming more and more important.

Human beings are also natural pattern-seekers. There’s even a special term used in psychological research literature to denote how this capacity makes us unique: superior pattern processing (SPP). A study in Frontiers in Neuroscience describes this phenomenon as the “fundamental basis of most, if not all, unique features of the human brain including intelligence, language, imagination, invention, and the belief in imaginary entities…”

When this ability is coupled with effective education about cyberthreats, it turns the brain into a formidable piece of cybersecurity hardware. To take just one example: According to FBI data, the costliest type of cyberattack (by far) is what’s known as “business email compromise,” or BEC. To execute this attack, a hacker will either use a fake email account designed to look like it belongs to a high-ranking figure in a company (the CEO or CFO, for instance), or will actually take over their email account, to manipulate someone else in the company into disclosing sensitive information, making an unauthorized transfer of funds, etc.

How Education Plays a Role in Defending against Cyberthreats

Let’s say a hacker decides to pose as a CEO. He or she could send the CFO an “urgent” email demanding an immediate payment to a supplier or some other entity. By placing the CFO under pressure to act quickly, the hacker makes it more likely that the CFO will transfer the funds into a fraudulent account without verifying the authenticity of the request. The FBI reports that this type of cyberattack cost companies almost $1.3 billion in 2018 and almost $1.8 billion last year.

But if employees, managers, and members of the C-suite are educated about cyberthreats, their pattern-seeking systems can identify and prevent BEC attacks. For example, one of the clearest signs of a fraudulent message can be found in the email headers – if you see a domain name that doesn’t align with the company you’re communicating with, misspellings, long strings of numbers, unknown and unrelated recipients, or any other strange elements in an email header, the alarm bells should be ringing. And even when the email account itself is infiltrated, the attack can be identified by noticing suspicious changes in behavior. If the CEO seems reckless or rushed, or claims to be unavailable for the remainder of the day, his or her colleagues should confirm any request before acting (especially if money or sensitive information is involved). This is another form of pattern recognition.

While the human brain can be a serious cybersecurity liability, it can also be the last line of defense against the increasingly sophisticated cyberthreats that companies and other organizations face. Despite the common impression that hackers only go after vulnerable digital systems, the reality is much more disturbing: they go after human beings. Social engineering is by far the most common type of cyberattack, and hackers are always devising new ways to fool and manipulate people.

However, because human error is so often the problem, human intelligence is the solution. Although it’s alarming how adept hackers have become at exploiting our psychological weaknesses, we should never forget that we have the cognitive equipment to turn those weaknesses into strengths.

The post The Human Brain is Both a Liability and Asset for Cybersecurity: Here’s Why appeared first on Artificial Intelligence.

An artificial intelligence learning technique has been used to make a breakthrough in understanding several previously unexplained features of the human brain

Researchers at Google-owned DeepMind discovered that a recent development in computer science regarding reinforcement learning could be applied to how the brain’s dopamine system works.

The research, published in the scientific journal Nature, has implications for better understanding mental health, as well as for learning and motivation disorders.

It found evidence that something referred to as “distributional reinforcement learning” used in AI algorithms actually mimics the dopamine reward system within the brain.

The technique allows the brain to use distribute the probability of future rewards rather than focussing on actions that result in immediate rewards.

“We found that dopamine neurons in the brain were each tuned to different levels of pessimism or optimism,” the researchers explained in a blog post describing their discovery.

“If they were a choir, they wouldn’t all be singing the same note, but harmonising – each with a consistent vocal register, like bass and soprano singers.

“In artificial reinforcement learning systems, this diverse tuning creates a richer training signal that greatly speeds learning in neural networks, and we speculate that the brain might use it for the same reason.”

Typically, it is AI research that borrows from neuroscience in order to create algorithms and machines capable of replicating the human brain. 

DeepMind has previously taken inspiration from biology to create neural networks capable of mastering Atari computer games to a superhuman level.

However, the firm says that the latest findings are proof that neuroscience can also benefit from AI research to push forward scientific discovery – a process referred to as the “virtuous circle”.

“The existence of distributional reinforcement learning in the brain has interesting implications for both AI and neuroscience,” the researchers conclude.

“We hope that asking and answering these questions will stimulate progress in neuroscience that will feed back to benefit AI research, completing the virtuous circle.”

The post ARTIFICIAL INTELLIGENCE: DEEPMIND UNLOCKS SECRETS OF HUMAN BRAIN USING AI LEARNING TECHNIQUE appeared first on Artificial Intelligence.

When it comes to advancing the field of artificial intelligence, the ultimate prize is still clear. The goal is to come as close as possible to the power of the human brain.

For researchers at the forefront of AI development, such as Naveen Rao (pictured), vice president and general manager of the artificial intelligence products group at Intel Corp., achieving near parity with a human’s cognitive ability remains a long way off.

“Back in 2013, there were 10 million or 20 million parameters, which was very large for a machine-learning model,” Rao said. “Now they’re in the billions. The human brain is 300 trillion to 500 trillion models, so we’re still pretty far away from that; we’ve got a long way to go.”

Rao spoke with Dave Vellante, host of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, and guest host Justin Warren, chief analyst at PivotNine Pty Ltd., during Amazon Web Services Inc.’s re:Invent conference in Las Vegas. They discussed the role of Intel’s processor technology in machine learning, intelligence for cloud and edge computing, the impact of recent neural network training tools, AI for good and the future of autonomous cars. (* Disclosure below.)

This week, theCUBE features Naveen Rao as its Guest of the Week.

Research advances AI

While the processing gap remains sizable, Rao and Intel are working on several projects to move AI forward. It is work not only fundamental to the field, but also integral to Intel’s own business strategy and long-term future.

Intel’s PC chip business still accounts for approximately half of its total revenue, but the second-largest segment revolves around the data center where AI is having the greatest impact. The company has been adjusting its powerful Xeon central processing unit chips to handle complex machine-learning tasks, most recently adding DL Boost to facilitate neural net performance.

As developers and data scientists iterate large data sets to generate a series of outcomes, the inference of how results are rolled out and deployed becomes more significant.

“Inference is all about the best performance per watt,” Rao explained. “How much processing can I shove into a particular time and power budget? On the training side, it’s much more about what kind of flexibility I have for exploring different types of models and training them very fast.”

Acquisitions bolster portfolio
One indicator of how seriously Intel is taking its role as a provider of AI processing in the data center can be found in its acquisition of Israel-based Habana Labs Ltd. for $2 billion in December. Habana Labs’ Goya AI Inference Processor is currently used by Facebook Inc. for its own machine-learning compiler.

Intel’s acquisition of Habana Labs followed other moves the company has made in the AI space since 2016 when it purchased Nervana Inc., where Rao served as co-founder and chief executive officer. In 2018, Intel bought Vertex.Ai and its platform-agnostic AI model technology and last year open-sourced its deep neural network framework, nGraph.

In November, Intel introduced its Nervana Neural Network Processors for training and inference, designed to accelerate AI system deployment from cloud to edge.

“From its very inception, the machine was really meant to be something that recapitulated intelligence,” Rao said. “Everything we do is impacted by AI and will be in service of building better AI platforms for intelligence at the edge, intelligence in the cloud, and everything in between.”

Training neural networks
Building better AI platforms will require training deep neural networks to run more powerfully in data centers today. But for these networks to become truly effective, they must be able to generalize to understand a range of possibilities while improving overall intelligence. Welcome to the world of the 16-bit brain floating point and generative adversarial networks, or GANs.

Intel will soon begin leveraging the floating point, or “bfloat16,” instruction for its Cooper Lake Xeon processors and Nervana-based training models. AI researchers have found that bfloat16 worked well across workloads and can be used for vision, speech and language applications, which explains why Intel is moving boldly down that path.

The instruction is also useful in helping move key learning networks forward, such as GANs. Using generative adversarial networks has been called “the most interesting idea in the last 10 years in machine learning” by Yann LeCun, director of AI research at Facebook.

“You can think of it as two competing sides of solving a problem,” Rao explained. “If you have two neural networks that are working against each other, one is generating stuff and the other one is asking if it’s fake or not. Eventually, you keep improving each other.”

Deepfakes remain a concern
Discussion of AI continues to center around the positive and negative. While GANs may indeed be instrumental in moving machine intelligence forward, they are also a key ingredient in creating “deepfakes,” which is raising alarm in some sectors of the tech community.

Deepfake technology has been used to create deceptive videos and nonconsensual pornography and even to disseminate fictitious news reports. One Forrester Research Inc. analyst has estimated that deepfake scams will exceed $250 million for the coming year.

Despite those concerns, Rao believes that the good will overcome the bad.

“One radiologist plus AI equals 100 radiologists,” Rao said. “It solves problems that we have in healthcare today; that’s where we should be going with this. I look at AI as a way to push humanity to the next level.”

In an AI-driven world, what will humanity at the next level look like? The continued march toward autonomous driving has the potential to impact human lives in a major way.

The fastest-growing business for Intel on an annualized basis is Mobileye Technologies Ltd., a company it acquired for $15 billion two years ago. Mobileye makes autonomous vehicle technology and is focused on the robotaxi market.

Autonomous vehicles provide yet another example of how Intel is moving from a PC-centered company to a data-driven business, and self-driving cars will be an inevitable outcome of AI progress, according to Rao.

“Autonomous driving is a bit of a black box, and the number of situations one can incur on the road are almost limitless,” Rao said. “For a 16-year-old, we say go out and drive. And, eventually, they sort of learn it. The same thing is happening now for autonomous systems.”

Driving cars is an area that Rao knows quite well. When he’s not guiding Intel’s AI products group, the technologist races semi-professionally on the Ferrari automotive circuit.

And while he envisions a world where autonomous cars will become a normal part of daily life, Rao doesn’t see human-driven cars disappearing completely.

“Five to seven years from now, we will be using autonomy much more on prescribed routes,” Rao said. “It won’t be that it completely replaces a human driver even in that time frame because it’s a very hard problem to solve. It’s going to be a gentle evolution over the next 20 to 30 years.”

The post Intel’s focus on AI maturation guides its data center strategy appeared first on Artificial Intelligence.

If we were to strip away artificial intelligence (AI) as we know it today, I’m not convinced humans would know how to cope with life.

Without AI, there’d be no Waze or Google Maps to show us where to go. There would be no Siri or Alexa to handle our Google searches or schedule a meeting with the CIO. Boeing 777 pilots only actually fly the plane for seven minutes , with much of the rest being done by AI technology.

There’d be no marketing automation.
No clever sales tools pulling customers in.
No process automation or business insights.
No chatbots answering simple – and frequent – customer queries.

AI already does a lot of the “thinking” for us. It’s been telling us what to do for years and we listen to it because we know it’s right. We could argue that this makes us lazy, but it has also liberated us from life’s mundane tasks, giving us more time to create, to think deeply about business and societal problems, and to solve them in new and exciting ways – or prevent them entirely.

It’s only the beginning
The AI market is growing at an astounding rate. IDC predicts that it will exceed $79 billion by 2022 and Gartner has said that, by 2020, AI will be a top five investment priority for more than 30% of CIOs.

And we’re only at the narrow intelligence stage. What happens when we start nearing general intelligence? Or super intelligence ?

For now, we’re still smarter than the machines. They give us data and we decide what to do with it. We tell them what to look for, what to stop looking for, and how to tell the difference in future. But the goal with general AI is to successfully mimic the human brain so that machines don’t need us to tell them what to do. What happens when that happens?

Not so easy
Before we answer that, think about the human brain for a moment. It processes data rapidly but also applies intuition, creativity, and empathy when making decisions. Machines can’t – and may never – emulate human emotion, which is why AI will always need human intelligence to support it. We created it, after all.

There’s no doubt that smart people will also create Artificial Neural Networks that will think and act like humans. Machines will analyse complex, real-time data and decide what to do for themselves. We may have no choice but to accept their decisions, unless we want to spend decades analysing data that AI already processed – in seconds.

In the amount of time it takes Waze to calculate a route, AI algorithms will predict natural disasters, so response teams can act faster and more effectively. It will analyse your family’s medical history to create a personalised treatment plan and improve your chances of recovery. This after your smartwatch told you to see your doctor immediately because you were at risk of a heart attack.

No AI without humans
The point is, there’s not much point to AI if there aren’t humans on the ground making things happen: emergency teams saving lives, doctors monitoring patients’ vitals and treatment response, visionary business leaders using AI to transform industries.

AI has given human intelligence room to breathe and expand. In business, cloud computing, Software-as-a-Service, and process automation reduce the burden of admin and provide the insights and visibility that businesses need to cut through the complexity and stay competitive. AI transforms how enterprises manage their people, processes, and operations, to offer better customer service, boost productivity, and help drive their businesses forward through innovative technology.

Human intelligence and artificial intelligence are complementary, symbiotic, inseparable. There is no one without the other. Yes, machines may become smarter than us, but isn’t that a good thing? When we know exactly what to do, we move faster and get better results. And that’s what we’ve been trying to achieve for decades.

The post AI: What has it done to human intelligence? appeared first on Artificial Intelligence.

“The fundamental questions cognitive neuroscientists and computer scientists seek to answer are similar,” says Aude Oliva of MIT. “They have a complex system made of components — for one, it’s called neurons and for the other, it’s called units — and we are doing experiments to try to determine what those components calculate.”

In Oliva’s work, which she is presenting at the CNS symposium, neuroscientists are learning much about the role of contextual clues in human image recognition. By using “artificial neurons” — essentially lines of code, software — with neural network models, they can parse out the various elements that go into recognizing a specific place or object.

“The brain is a deep and complex neural network,” says Nikolaus Kriegeskorte of Columbia University, who is chairing the symposium. “Neural network models are brain-inspired models that are now state-of-the-art in many artificial intelligence applications, such as computer vision.”

In one recent study of more than 10 million images, Oliva and colleagues taught an artificial network to recognize 350 different places, such as a kitchen, bedroom, park, living room, etc. They expected the network to learn objects such as a bed associated with a bedroom. What they didn’t expect was that the network would learn to recognize people and animals, for example dogs at parks and cats in living rooms.

The machine intelligence programs learn very quickly when given lots of data, which is what enables them to parse contextual learning at such a fine level, Oliva says. While it is not possible to dissect human neurons at such a level, the computer model performing a similar task is entirely transparent. The artificial neural networks serve as “mini-brains that can be studied, changed, evaluated, compared against responses given by human neural networks, so the cognitive neuroscientists have some sort of sketch of how a real brain may function.”

Indeed, Kriegeskorte says that these models have helped neuroscientists understand how people can recognize the objects around them in the blink of an eye. “This involves millions of signals emanating from the retina, that sweep through a sequence of layers of neurons, extracting semantic information, for example that we’re looking at a street scene with several people and a dog,” he says. “Current neural network models can perform this kind of task using only computations that biological neurons can perform. Moreover, these neural network models can predict to some extent how a neuron deep in the brain will respond to any image.”

Using computer science to understand the human brain is a relatively new field that is expanding rapidly thanks to advancements in computing speed and power, along with neuroscience imaging tools. The artificial networks cannot yet replicate human visual abilities, Kriegeskorte says, but by modeling the human brain, they are furthering understanding of both cognition and artificial intelligence. “It’s a uniquely exciting time to be working at the intersection of neuroscience, cognitive science, and AI,” he says.

Indeed, Oliva says; “Human cognitive and computational neuroscience is a fast-growing area of research, and knowledge about how the human brain is able to see, hear, feel, think, remember, and predict is mandatory to develop better diagnostic tools, to repair the brain, and to make sure it develops well.”

The post Dissecting artificial intelligence to better understand the human brain appeared first on Artificial Intelligence.

Brain’s dynamic properties, how it is wired and also how that wiring shifts in response to changing intellectual demands, are the best predictors of intelligence in the human brain, a study of the University of Illinois (UI) found.

“There are the pathways that encode prior knowledge and experience, which we call ‘crystallized intelligence.’ And there are adaptive reasoning and problem-solving skills that are quite flexible, called ‘fluid intelligence,'” said UI psychology professor Aron Barbey, who hosted the study.

Crystallized intelligence involves robust connections, the result of months or years of neural traffic on well-worn pathways. Fluid intelligence involves weaker, more transient pathways and connections that are formed when the brain tackles unique or unusual problems.

“Rather than forming permanent connections, we are constantly updating our prior knowledge, and this involves forming new connections,” Barbey said. The more readily the brain forms and reforms its connectivity in response to changing needs, the better it works, he said.

Researchers have long known that flexibility is an important characteristic of human brain function. But only recently has the idea emerged that flexibility provides the basis for human intelligence.

General intelligence requires not only the ability to flexibly reach nearby and easy-to-access states to support crystallized intelligence, but also the ability to adapt and reach difficult-to-access states to support fluid intelligence, Barbey said.

“What my colleagues and I have come to realize is that general intelligence does not originate from a single brain region or network. Emerging neuroscience evidence instead suggests that intelligence reflects the ability to flexibly transition between network states,” he said.

The study has been published in the journal Trends in Cognitive Sciences.

The post Flexibility, heart of human intelligence: study appeared first on Artificial Intelligence.

You’ve probably encountered the term “machine learning” more than a few times lately. Often used interchangeably with artificial intelligence, machine learning is in fact a subset of AI, both of which can trace their roots to MIT in the late 1950s.

Machine learning is something you probably encounter every day, whether you know it or not. The Siri and Alexa voice assistants, Facebook’s and Microsoft’s facial recognition, Amazon and Netflix recommendations, the technology that keeps self-driving cars from crashing into things – all are a result of advances in machine learning.

While still nowhere near as complex as a human brain, systems based on machine learning have achieved some impressive feats, like defeating human challengers at chess, Jeopardy, Go, and Texas Hold ‘em.

Dismissed for decades as overhyped and unrealistic (the infamous ”AI winter”), both AI and machine learning have enjoyed a huge resurgence over the last few years, thanks to a number of technological breakthroughs, a massive explosion in cheap computing horsepower, and a bounty of data for machine learning models to chew on.

Self-taught software

So what is machine learning, exactly? Let’s start by noting what it is not: a conventional, hand-coded, human-programmed computing application.

Unlike traditional software, which is great at following instructions but terrible at improvising, machine learning systems essentially code themselves, developing their own instructions by generalizing from examples.

The classic example is image recognition. Show a machine learning system enough photos of dogs (labeled “dogs”), as well as pictures of cats, trees, babies, bananas, or any other object (labeled “not dogs”), and if the system is trained correctly it will eventually get good at identifying canines, without a human being ever telling it what a dog is supposed to look like.

The spam filter in your email program is a good example of machine learning in action. After being exposed to hundreds of millions of spam samples, as well as non-spam email, it has learned to identify the key characteristics of those nasty unwanted messages. It’s not perfect, but it’s usually pretty accurate.

Supervised vs. unsupervised learning

This kind of machine learning is called supervised learning, which means that someone exposed the machine learning algorithm to an enormous set of training data, examined its output, then continuously tweaked its settings until it produced the expected result when shown data it had not seen before. (This is analogous to clicking the “not spam” button in your inbox when the filter traps a legitimate message by accident. The more you do that, the more the accuracy of the filter should improve.)

The most common supervised learning tasks involve classification and prediction (i.e, “regression”). Spam detection and image recognition are both classification problems. Predicting stock prices is a classic example of a regression problem.

A second kind of machine learning is called unsupervised learning. This is where the system pores over vast amounts of data to learn what “normal” data looks like, so it can detect anomalies and hidden patterns. Unsupervised machine learning is useful when you don’t really know what you’re looking for, so you can’t train the system to find it.

Unsupervised machine learning systems can identify patterns in vast amounts of data many times faster than humans can, which is why banks use them to flag fraudulent transactions, marketers deploy them to identify customers with similar attributes, and security software employs them to detect hostile activity on a network.

Clustering and association rule learning are two examples of unsupervised learning algorithms. Clustering is the secret sauce behind customer segmentation, for example, while association rule learning is used for recommendation engines.

Limitations of machine learning

Because each machine learning system creates its own connections, how a particular one actually works can be a bit of a black box. You can’t always reverse engineer the process to discover why your system can distinguish between a Pekingese and a Persian. As long as it works, it doesn’t really matter.

But a machine learning system is only as good as the data it has been exposed to – the classic example of “garbage in, garbage out.” When poorly trained or exposed to an insufficient data set, a machine learning algorithm can produce results that are not only wrong but discriminatory.

HP got into trouble back in 2009 when facial recognition technology built into the webcam on an HP MediaSmart laptop was able to unable to detect the faces of African Americans. In June 2015, faulty algorithms in the Google Photos app mislabeled two black Americans as gorillas.

Another dramatic example: Microsoft’s ill-fated Taybot, a March 2016 experiment to see if an AI system could emulate human conversation by learning from tweets. In less than a day, malicious Twitter trolls had turned Tay into a hate-speech-spewing chat bot from hell. Talk about corrupted training data.

A machine learning lexicon

But machine learning is really just the tip of the AI berg. Other terms closely associated with machine learning are neural networks, deep learning, and cognitive computing.

Neural network. A computer architecture designed to mimic the structure of neurons in our brains, with each artificial neuron (microcircuit) connecting to other neurons inside the system. Neural networks are arranged in layers, with neurons in one layer passing data to multiple neurons in the next layer, and so on, until eventually they reach the output layer. This final layer is where the neural network presents its best guesses as to, say, what that dog-shaped object was, along with a confidence score.

There are multiple types of neural networks for solving different types of problems. Networks with large numbers of layers are called “deep neural networks.” Neural nets are some of the most important tools used in machine learning scenarios, but not the only ones.

Deep learning. This is essentially machine learning on steroids, using multi-layered (deep) neural networks to arrive at decisions based on “imperfect” or incomplete information. The deep learning system DeepStack is what defeated 11 professional poker players last December, by constantly recomputing its strategy after each round of bets.

Cognitive computing. This is the term favored by IBM, creators of Watson, the supercomputer that kicked humanity’s ass at Jeopardy in 2011. The difference between cognitive computing and artificial intelligence, in IBM’s view, is that instead of replacing human intelligence, cognitive computing is designed to augment it—enabling doctors to diagnose illnesses more accurately, financial managers to make smarter recommendations, lawyers to search caselaw more quickly, and so on.

This, of course, is an extremely superficial overview. Those who want to dive more deeply into the intricacies of AI and machine learning can start with this semi-wonky tutorial from the University of Washington’s Pedro Domingos, or this series of Medium posts from Adam Geitgey, as well as “What deep learning really means” by InfoWorld’s Martin Heller.

Despite all the hype about AI, it’s not an overstatement to say that machine learning and the technologies associated with it are changing the world as we know it. Best to learn about it now, before the machines become fully self-aware.

The post What is machine learning? Software derived from data appeared first on Artificial Intelligence.