Tag Archives: programmed

#432568 Tech Optimists See a Golden ...

Technology evangelists dream about a future where we’re all liberated from the more mundane aspects of our jobs by artificial intelligence. Other futurists go further, imagining AI will enable us to become superhuman, enhancing our intelligence, abandoning our mortal bodies, and uploading ourselves to the cloud.

Paradise is all very well, although your mileage may vary on whether these scenarios are realistic or desirable. The real question is, how do we get there?

Economist John Maynard Keynes notably argued in favor of active intervention when an economic crisis hits, rather than waiting for the markets to settle down to a more healthy equilibrium in the long run. His rebuttal to critics was, “In the long run, we are all dead.” After all, if it takes 50 years of upheaval and economic chaos for things to return to normality, there has been an immense amount of human suffering first.

Similar problems arise with the transition to a world where AI is intimately involved in our lives. In the long term, automation of labor might benefit the human species immensely. But in the short term, it has all kinds of potential pitfalls, especially in exacerbating inequality within societies where AI takes on a larger role. A new report from the Institute for Public Policy Research has deep concerns about the future of work.

Uneven Distribution
While the report doesn’t foresee the same gloom and doom of mass unemployment that other commentators have considered, the concern is that the gains in productivity and economic benefits from AI will be unevenly distributed. In the UK, jobs that account for £290 billion worth of wages in today’s economy could potentially be automated with current technology. But these are disproportionately jobs held by people who are already suffering from social inequality.

Low-wage jobs are five times more likely to be automated than high-wage jobs. A greater proportion of jobs held by women are likely to be automated. The solution that’s often suggested is that people should simply “retrain”; but if no funding or assistance is provided, this burden is too much to bear. You can’t expect people to seamlessly transition from driving taxis to writing self-driving car software without help. As we have already seen, inequality is exacerbated when jobs that don’t require advanced education (even if they require a great deal of technical skill) are the first to go.

No Room for Beginners
Optimists say algorithms won’t replace humans, but will instead liberate us from the dull parts of our jobs. Lawyers used to have to spend hours trawling through case law to find legal precedents; now AI can identify the most relevant documents for them. Doctors no longer need to look through endless scans and perform diagnostic tests; machines can do this, leaving the decision-making to humans. This boosts productivity and provides invaluable tools for workers.

But there are issues with this rosy picture. If humans need to do less work, the economic incentive is for the boss to reduce their hours. Some of these “dull, routine” parts of the job were traditionally how people getting into the field learned the ropes: paralegals used to look through case law, but AI may render them obsolete. Even in the field of journalism, there’s now software that will rewrite press releases for publication, traditionally something close to an entry-level task. If there are no entry-level jobs, or if entry-level now requires years of training, the result is to exacerbate inequality and reduce social mobility.

Automating Our Biases
The adoption of algorithms into employment has already had negative impacts on equality. Cathy O’Neil, mathematics PhD from Harvard, raises these concerns in her excellent book Weapons of Math Destruction. She notes that algorithms designed by humans often encode the biases of that society, whether they’re racial or based on gender and sexuality.

Google’s search engine advertises more executive-level jobs to users it thinks are male. AI programs predict that black offenders are more likely to re-offend than white offenders; they receive correspondingly longer sentences. It needn’t necessarily be that bias has been actively programmed; perhaps the algorithms just learn from historical data, but this means they will perpetuate historical inequalities.

Take candidate-screening software HireVue, used by many major corporations to assess new employees. It analyzes “verbal and non-verbal cues” of candidates, comparing them to employees that historically did well. Either way, according to Cathy O’Neil, they are “using people’s fear and trust of mathematics to prevent them from asking questions.” With no transparency or understanding of how the algorithm generates its results, and no consensus over who’s responsible for the results, discrimination can occur automatically, on a massive scale.

Combine this with other demographic trends. In rich countries, people are living longer. An increasing burden will be placed on a shrinking tax base to support that elderly population. A recent study said that due to the accumulation of wealth in older generations, millennials stand to inherit more than any previous generation, but it won’t happen until they’re in their 60s. Meanwhile, those with savings and capital will benefit as the economy shifts: the stock market and GDP will grow, but wages and equality will fall, a situation that favors people who are already wealthy.

Even in the most dramatic AI scenarios, inequality is exacerbated. If someone develops a general intelligence that’s near-human or super-human, and they manage to control and monopolize it, they instantly become immensely wealthy and powerful. If the glorious technological future that Silicon Valley enthusiasts dream about is only going to serve to make the growing gaps wider and strengthen existing unfair power structures, is it something worth striving for?

What Makes a Utopia?
We urgently need to redefine our notion of progress. Philosophers worry about an AI that is misaligned—the things it seeks to maximize are not the things we want maximized. At the same time, we measure the development of our countries by GDP, not the quality of life of workers or the equality of opportunity in the society. Growing wealth with increased inequality is not progress.

Some people will take the position that there are always winners and losers in society, and that any attempt to redress the inequalities of our society will stifle economic growth and leave everyone worse off. Some will see this as an argument for a new economic model, based around universal basic income. Any moves towards this will need to take care that it’s affordable, sustainable, and doesn’t lead towards an entrenched two-tier society.

Walter Schiedel’s book The Great Leveller is a huge survey of inequality across all of human history, from the 21st century to prehistoric cave-dwellers. He argues that only revolutions, wars, and other catastrophes have historically reduced inequality: a perfect example is the Black Death in Europe, which (by reducing the population and therefore the labor supply that was available) increased wages and reduced inequality. Meanwhile, our solution to the financial crisis of 2007-8 may have only made the problem worse.

But in a world of nuclear weapons, of biowarfare, of cyberwarfare—a world of unprecedented, complex, distributed threats—the consequences of these “safety valves” could be worse than ever before. Inequality increases the risk of global catastrophe, and global catastrophes could scupper any progress towards the techno-utopia that the utopians dream of. And a society with entrenched inequality is no utopia at all.

Image Credit: OliveTree / Shutterstock.com Continue reading

Posted in Human Robots

#432051 What Roboticists Are Learning From Early ...

You might not have heard of Hanson Robotics, but if you’re reading this, you’ve probably seen their work. They were the company behind Sophia, the lifelike humanoid avatar that’s made dozens of high-profile media appearances. Before that, they were the company behind that strange-looking robot that seemed a bit like Asimo with Albert Einstein’s head—or maybe you saw BINA48, who was interviewed for the New York Times in 2010 and featured in Jon Ronson’s books. For the sci-fi aficionados amongst you, they even made a replica of legendary author Philip K. Dick, best remembered for having books with titles like Do Androids Dream of Electric Sheep? turned into films with titles like Blade Runner.

Hanson Robotics, in other words, with their proprietary brand of life-like humanoid robots, have been playing the same game for a while. Sometimes it can be a frustrating game to watch. Anyone who gives the robot the slightest bit of thought will realize that this is essentially a chat-bot, with all the limitations this implies. Indeed, even in that New York Times interview with BINA48, author Amy Harmon describes it as a frustrating experience—with “rare (but invariably thrilling) moments of coherence.” This sensation will be familiar to anyone who’s conversed with a chatbot that has a few clever responses.

The glossy surface belies the lack of real intelligence underneath; it seems, at first glance, like a much more advanced machine than it is. Peeling back that surface layer—at least for a Hanson robot—means you’re peeling back Frubber. This proprietary substance—short for “Flesh Rubber,” which is slightly nightmarish—is surprisingly complicated. Up to thirty motors are required just to control the face; they manipulate liquid cells in order to make the skin soft, malleable, and capable of a range of different emotional expressions.

A quick combinatorial glance at the 30+ motors suggests that there are millions of possible combinations; researchers identify 62 that they consider “human-like” in Sophia, although not everyone agrees with this assessment. Arguably, the technical expertise that went into reconstructing the range of human facial expressions far exceeds the more simplistic chat engine the robots use, although it’s the second one that allows it to inflate the punters’ expectations with a few pre-programmed questions in an interview.

Hanson Robotics’ belief is that, ultimately, a lot of how humans will eventually relate to robots is going to depend on their faces and voices, as well as on what they’re saying. “The perception of identity is so intimately bound up with the perception of the human form,” says David Hanson, company founder.

Yet anyone attempting to design a robot that won’t terrify people has to contend with the uncanny valley—that strange blend of concern and revulsion people react with when things appear to be creepily human. Between cartoonish humanoids and genuine humans lies what has often been a no-go zone in robotic aesthetics.

The uncanny valley concept originated with roboticist Masahiro Mori, who argued that roboticists should avoid trying to replicate humans exactly. Since anything that wasn’t perfect, but merely very good, would elicit an eerie feeling in humans, shirking the challenge entirely was the only way to avoid the uncanny valley. It’s probably a task made more difficult by endless streams of articles about AI taking over the world that inexplicably conflate AI with killer humanoid Terminators—which aren’t particularly likely to exist (although maybe it’s best not to push robots around too much).

The idea behind this realm of psychological horror is fairly simple, cognitively speaking.

We know how to categorize things that are unambiguously human or non-human. This is true even if they’re designed to interact with us. Consider the popularity of Aibo, Jibo, or even some robots that don’t try to resemble humans. Something that resembles a human, but isn’t quite right, is bound to evoke a fear response in the same way slightly distorted music or slightly rearranged furniture in your home will. The creature simply doesn’t fit.

You may well reject the idea of the uncanny valley entirely. David Hanson, naturally, is not a fan. In the paper Upending the Uncanny Valley, he argues that great art forms have often resembled humans, but the ultimate goal for humanoid roboticists is probably to create robots we can relate to as something closer to humans than works of art.

Meanwhile, Hanson and other scientists produce competing experiments to either demonstrate that the uncanny valley is overhyped, or to confirm it exists and probe its edges.

The classic experiment involves gradually morphing a cartoon face into a human face, via some robotic-seeming intermediaries—yet it’s in movement that the real horror of the almost-human often lies. Hanson has argued that incorporating cartoonish features may help—and, sometimes, that the uncanny valley is a generational thing which will melt away when new generations grow used to the quirks of robots. Although Hanson might dispute the severity of this effect, it’s clearly what he’s trying to avoid with each new iteration.

Hiroshi Ishiguro is the latest of the roboticists to have dived headlong into the valley.

Building on the work of pioneers like Hanson, those who study human-robot interaction are pushing at the boundaries of robotics—but also of social science. It’s usually difficult to simulate what you don’t understand, and there’s still an awful lot we don’t understand about how we interpret the constant streams of non-verbal information that flow when you interact with people in the flesh.

Ishiguro took this imitation of human forms to extreme levels. Not only did he monitor and log the physical movements people made on videotapes, but some of his robots are based on replicas of people; the Repliee series began with a ‘replicant’ of his daughter. This involved making a rubber replica—a silicone cast—of her entire body. Future experiments were focused on creating Geminoid, a replica of Ishiguro himself.

As Ishiguro aged, he realized that it would be more effective to resemble his replica through cosmetic surgery rather than by continually creating new casts of his face, each with more lines than the last. “I decided not to get old anymore,” Ishiguro said.

We love to throw around abstract concepts and ideas: humans being replaced by machines, cared for by machines, getting intimate with machines, or even merging themselves with machines. You can take an idea like that, hold it in your hand, and examine it—dispassionately, if not without interest. But there’s a gulf between thinking about it and living in a world where human-robot interaction is not a field of academic research, but a day-to-day reality.

As the scientists studying human-robot interaction develop their robots, their replicas, and their experiments, they are making some of the first forays into that world. We might all be living there someday. Understanding ourselves—decrypting the origins of empathy and love—may be the greatest challenge to face. That is, if you want to avoid the valley.

Image Credit: Anton Gvozdikov / Shutterstock.com Continue reading

Posted in Human Robots

#431987 OptoForce Industrial Robot Sensors

OptoForce Sensors Providing Industrial Robots with

a “Sense of Touch” to Advance Manufacturing Automation

Global efforts to expand the capabilities of industrial robots are on the rise, as the demand from manufacturing companies to strengthen their operations and improve performance grows.

Hungary-based OptoForce, with a North American office in Charlotte, North Carolina, is one company that continues to support organizations with new robotic capabilities, as evidenced by its several new applications released in 2017.

The company, a leading robotics technology provider of multi-axis force and torque sensors, delivers 6 degrees of freedom force and torque measurement for industrial automation, and provides sensors for most of the currently-used industrial robots.

It recently developed and brought to market three new applications for KUKA industrial robots.

The new applications are hand guiding, presence detection, and center pointing and will be utilized by both end users and systems integrators. Each application is summarized below and what they provide for KUKA robots, along with video demonstrations to show how they operate.

Photo By: www.optoforce.com

Hand Guiding: With OptoForce’s Hand Guiding application, KUKA robots can easily and smoothly move in an assigned direction and selected route. This video shows specifically how to program the robot for hand guiding.

Presence Detection: This application allows KUKA robots to detect the presence of a specific object and to find the object even if it has moved. Visit here to learn more about presence detection.
Center Pointing: With this application, the OptoForce sensor helps the KUKA robot find the center point of an object by providing the robot with a sense of touch. This solution also works with glossy metal objects where a vision system would not be able to define its position. This video shows in detail how the center pointing application works.

The company’s CEO explained how these applications help KUKA robots and industrial automation.

Photo By: www.optoforce.com
“OptoForce’s new applications for KUKA robots pave the way for substantial improvements in industrial automation for both end users and systems integrators,” said Ákos Dömötör, CEO of OptoForce. “Our 6-axis force/torque sensors are combined with highly functional hardware and a comprehensive software package, which include the pre-programmed industrial applications. Essentially, we’re adding a ‘sense of touch’ to KUKA robot arms, enabling these robots to have abilities similar to a human hand, and opening up numerous new capabilities in industrial automation.”

Along with these new applications recently released for KUKA robots, OptoForce sensors are also being used by various companies on numerous industrial robots and manufacturing automation projects around the world. Examples of other uses include: path recording, polishing plastic and metal, box insertion, placing pins in holes, stacking/destacking, palletizing, and metal part sanding.

Specifically, some of the projects current underway by companies include: a plastic parting line removal; an obstacle detection for a major car manufacturing company; and a center point insertion application for a car part supplier, where the task of the robot is to insert a mirror, completely centered, onto a side mirror housing.

For more information, visit www.optoforce.com.

This post was provided by: OptoForce

The post OptoForce Industrial Robot Sensors appeared first on Roboticmagazine. Continue reading

Posted in Human Robots

#431869 When Will We Finally Achieve True ...

The field of artificial intelligence goes back a long way, but many consider it was officially born when a group of scientists at Dartmouth College got together for a summer, back in 1956. Computers had, over the last few decades, come on in incredible leaps and bounds; they could now perform calculations far faster than humans. Optimism, given the incredible progress that had been made, was rational. Genius computer scientist Alan Turing had already mooted the idea of thinking machines just a few years before. The scientists had a fairly simple idea: intelligence is, after all, just a mathematical process. The human brain was a type of machine. Pick apart that process, and you can make a machine simulate it.
The problem didn’t seem too hard: the Dartmouth scientists wrote, “We think that a significant advance can be made in one or more of these problems if a carefully selected group of scientists work on it together for a summer.” This research proposal, by the way, contains one of the earliest uses of the term artificial intelligence. They had a number of ideas—maybe simulating the human brain’s pattern of neurons could work and teaching machines the abstract rules of human language would be important.
The scientists were optimistic, and their efforts were rewarded. Before too long, they had computer programs that seemed to understand human language and could solve algebra problems. People were confidently predicting there would be a human-level intelligent machine built within, oh, let’s say, the next twenty years.
It’s fitting that the industry of predicting when we’d have human-level intelligent AI was born at around the same time as the AI industry itself. In fact, it goes all the way back to Turing’s first paper on “thinking machines,” where he predicted that the Turing Test—machines that could convince humans they were human—would be passed in 50 years, by 2000. Nowadays, of course, people are still predicting it will happen within the next 20 years, perhaps most famously Ray Kurzweil. There are so many different surveys of experts and analyses that you almost wonder if AI researchers aren’t tempted to come up with an auto reply: “I’ve already predicted what your question will be, and no, I can’t really predict that.”
The issue with trying to predict the exact date of human-level AI is that we don’t know how far is left to go. This is unlike Moore’s Law. Moore’s Law, the doubling of processing power roughly every couple of years, makes a very concrete prediction about a very specific phenomenon. We understand roughly how to get there—improved engineering of silicon wafers—and we know we’re not at the fundamental limits of our current approach (at least, not until you’re trying to work on chips at the atomic scale). You cannot say the same about artificial intelligence.
Common Mistakes
Stuart Armstrong’s survey looked for trends in these predictions. Specifically, there were two major cognitive biases he was looking for. The first was the idea that AI experts predict true AI will arrive (and make them immortal) conveniently just before they’d be due to die. This is the “Rapture of the Nerds” criticism people have leveled at Kurzweil—his predictions are motivated by fear of death, desire for immortality, and are fundamentally irrational. The ability to create a superintelligence is taken as an article of faith. There are also criticisms by people working in the AI field who know first-hand the frustrations and limitations of today’s AI.
The second was the idea that people always pick a time span of 15 to 20 years. That’s enough to convince people they’re working on something that could prove revolutionary very soon (people are less impressed by efforts that will lead to tangible results centuries down the line), but not enough for you to be embarrassingly proved wrong. Of the two, Armstrong found more evidence for the second one—people were perfectly happy to predict AI after they died, although most didn’t, but there was a clear bias towards “15–20 years from now” in predictions throughout history.
Measuring Progress
Armstrong points out that, if you want to assess the validity of a specific prediction, there are plenty of parameters you can look at. For example, the idea that human-level intelligence will be developed by simulating the human brain does at least give you a clear pathway that allows you to assess progress. Every time we get a more detailed map of the brain, or successfully simulate another part of it, we can tell that we are progressing towards this eventual goal, which will presumably end in human-level AI. We may not be 20 years away on that path, but at least you can scientifically evaluate the progress.
Compare this to those that say AI, or else consciousness, will “emerge” if a network is sufficiently complex, given enough processing power. This might be how we imagine human intelligence and consciousness emerged during evolution—although evolution had billions of years, not just decades. The issue with this is that we have no empirical evidence: we have never seen consciousness manifest itself out of a complex network. Not only do we not know if this is possible, we cannot know how far away we are from reaching this, as we can’t even measure progress along the way.
There is an immense difficulty in understanding which tasks are hard, which has continued from the birth of AI to the present day. Just look at that original research proposal, where understanding human language, randomness and creativity, and self-improvement are all mentioned in the same breath. We have great natural language processing, but do our computers understand what they’re processing? We have AI that can randomly vary to be “creative,” but is it creative? Exponential self-improvement of the kind the singularity often relies on seems far away.
We also struggle to understand what’s meant by intelligence. For example, AI experts consistently underestimated the ability of AI to play Go. Many thought, in 2015, it would take until 2027. In the end, it took two years, not twelve. But does that mean AI is any closer to being able to write the Great American Novel, say? Does it mean it’s any closer to conceptually understanding the world around it? Does it mean that it’s any closer to human-level intelligence? That’s not necessarily clear.
Not Human, But Smarter Than Humans
But perhaps we’ve been looking at the wrong problem. For example, the Turing test has not yet been passed in the sense that AI cannot convince people it’s human in conversation; but of course the calculating ability, and perhaps soon the ability to perform other tasks like pattern recognition and driving cars, far exceed human levels. As “weak” AI algorithms make more decisions, and Internet of Things evangelists and tech optimists seek to find more ways to feed more data into more algorithms, the impact on society from this “artificial intelligence” can only grow.
It may be that we don’t yet have the mechanism for human-level intelligence, but it’s also true that we don’t know how far we can go with the current generation of algorithms. Those scary surveys that state automation will disrupt society and change it in fundamental ways don’t rely on nearly as many assumptions about some nebulous superintelligence.
Then there are those that point out we should be worried about AI for other reasons. Just because we can’t say for sure if human-level AI will arrive this century, or never, it doesn’t mean we shouldn’t prepare for the possibility that the optimistic predictors could be correct. We need to ensure that human values are programmed into these algorithms, so that they understand the value of human life and can act in “moral, responsible” ways.
Phil Torres, at the Project for Future Human Flourishing, expressed it well in an interview with me. He points out that if we suddenly decided, as a society, that we had to solve the problem of morality—determine what was right and wrong and feed it into a machine—in the next twenty years…would we even be able to do it?
So, we should take predictions with a grain of salt. Remember, it turned out the problems the AI pioneers foresaw were far more complicated than they anticipated. The same could be true today. At the same time, we cannot be unprepared. We should understand the risks and take our precautions. When those scientists met in Dartmouth in 1956, they had no idea of the vast, foggy terrain before them. Sixty years later, we still don’t know how much further there is to go, or how far we can go. But we’re going somewhere.
Image Credit: Ico Maker / Shutterstock.com Continue reading

Posted in Human Robots

#431836 Do Our Brains Use Deep Learning to Make ...

The first time Dr. Blake Richards heard about deep learning, he was convinced that he wasn’t just looking at a technique that would revolutionize artificial intelligence. He also knew he was looking at something fundamental about the human brain.
That was the early 2000s, and Richards was taking a course with Dr. Geoff Hinton at the University of Toronto. Hinton, a pioneer architect of the algorithm that would later take the world by storm, was offering an introductory course on his learning method inspired by the human brain.
The key words here are “inspired by.” Despite Richards’ conviction, the odds were stacked against him. The human brain, as it happens, seems to lack a critical function that’s programmed into deep learning algorithms. On the surface, the algorithms were violating basic biological facts already proven by neuroscientists.
But what if, superficial differences aside, deep learning and the brain are actually compatible?
Now, in a new study published in eLife, Richards, working with DeepMind, proposed a new algorithm based on the biological structure of neurons in the neocortex. Also known as the cortex, this outermost region of the brain is home to higher cognitive functions such as reasoning, prediction, and flexible thought.
The team networked their artificial neurons together into a multi-layered network and challenged it with a classic computer vision task—identifying hand-written numbers.
The new algorithm performed well. But the kicker is that it analyzed the learning examples in a way that’s characteristic of deep learning algorithms, even though it was completely based on the brain’s fundamental biology.
“Deep learning is possible in a biological framework,” concludes the team.
Because the model is only a computer simulation at this point, Richards hopes to pass the baton to experimental neuroscientists, who could actively test whether the algorithm operates in an actual brain.
If so, the data could then be passed back to computer scientists to work out the next generation of massively parallel and low-energy algorithms to power our machines.
It’s a first step towards merging the two fields back into a “virtuous circle” of discovery and innovation.
The blame game
While you’ve probably heard of deep learning’s recent wins against humans in the game of Go, you might not know the nitty-gritty behind the algorithm’s operations.
In a nutshell, deep learning relies on an artificial neural network with virtual “neurons.” Like a towering skyscraper, the network is structured into hierarchies: lower-level neurons process aspects of an input—for example, a horizontal or vertical stroke that eventually forms the number four—whereas higher-level neurons extract more abstract aspects of the number four.
To teach the network, you give it examples of what you’re looking for. The signal propagates forward in the network (like climbing up a building), where each neuron works to fish out something fundamental about the number four.
Like children trying to learn a skill the first time, initially the network doesn’t do so well. It spits out what it thinks a universal number four should look like—think a Picasso-esque rendition.
But here’s where the learning occurs: the algorithm compares the output with the ideal output, and computes the difference between the two (dubbed “error”). This error is then “backpropagated” throughout the entire network, telling each neuron: hey, this is how far off you were, so try adjusting your computation closer to the ideal.
Millions of examples and tweakings later, the network inches closer to the desired output and becomes highly proficient at the trained task.
This error signal is crucial for learning. Without efficient “backprop,” the network doesn’t know which of its neurons are off kilter. By assigning blame, the AI can better itself.
The brain does this too. How? We have no clue.
Biological No-Go
What’s clear, though, is that the deep learning solution doesn’t work.
Backprop is a pretty needy function. It requires a very specific infrastructure for it to work as expected.
For one, each neuron in the network has to receive the error feedback. But in the brain, neurons are only connected to a few downstream partners (if that). For backprop to work in the brain, early-level neurons need to be able to receive information from billions of connections in their downstream circuits—a biological impossibility.
And while certain deep learning algorithms adapt a more local form of backprop— essentially between neurons—it requires their connection forwards and backwards to be symmetric. This hardly ever occurs in the brain’s synapses.
More recent algorithms adapt a slightly different strategy, in that they implement a separate feedback pathway that helps the neurons to figure out errors locally. While it’s more biologically plausible, the brain doesn’t have a separate computational network dedicated to the blame game.
What it does have are neurons with intricate structures, unlike the uniform “balls” that are currently applied in deep learning.
Branching Networks
The team took inspiration from pyramidal cells that populate the human cortex.
“Most of these neurons are shaped like trees, with ‘roots’ deep in the brain and ‘branches’ close to the surface,” says Richards. “What’s interesting is that these roots receive a different set of inputs than the branches that are way up at the top of the tree.”
This is an illustration of a multi-compartment neural network model for deep learning. Left: Reconstruction of pyramidal neurons from mouse primary visual cortex. Right: Illustration of simplified pyramidal neuron models. Image Credit: CIFAR
Curiously, the structure of neurons often turn out be “just right” for efficiently cracking a computational problem. Take the processing of sensations: the bottoms of pyramidal neurons are right smack where they need to be to receive sensory input, whereas the tops are conveniently placed to transmit feedback errors.
Could this intricate structure be evolution’s solution to channeling the error signal?
The team set up a multi-layered neural network based on previous algorithms. But rather than having uniform neurons, they gave those in middle layers—sandwiched between the input and output—compartments, just like real neurons.
When trained with hand-written digits, the algorithm performed much better than a single-layered network, despite lacking a way to perform classical backprop. The cell-like structure itself was sufficient to assign error: the error signals at one end of the neuron are naturally kept separate from input at the other end.
Then, at the right moment, the neuron brings both sources of information together to find the best solution.
There’s some biological evidence for this: neuroscientists have long known that the neuron’s input branches perform local computations, which can be integrated with signals that propagate backwards from the so-called output branch.
However, we don’t yet know if this is the brain’s way of dealing blame—a question that Richards urges neuroscientists to test out.
What’s more, the network parsed the problem in a way eerily similar to traditional deep learning algorithms: it took advantage of its multi-layered structure to extract progressively more abstract “ideas” about each number.
“[This is] the hallmark of deep learning,” the authors explain.
The Deep Learning Brain
Without doubt, there will be more twists and turns to the story as computer scientists incorporate more biological details into AI algorithms.
One aspect that Richards and team are already eyeing is a top-down predictive function, in which signals from higher levels directly influence how lower levels respond to input.
Feedback from upper levels doesn’t just provide error signals; it could also be nudging lower processing neurons towards a “better” activity pattern in real-time, says Richards.
The network doesn’t yet outperform other non-biologically derived (but “brain-inspired”) deep networks. But that’s not the point.
“Deep learning has had a huge impact on AI, but, to date, its impact on neuroscience has been limited,” the authors say.
Now neuroscientists have a lead they could experimentally test: that the structure of neurons underlie nature’s own deep learning algorithm.
“What we might see in the next decade or so is a real virtuous cycle of research between neuroscience and AI, where neuroscience discoveries help us to develop new AI and AI can help us interpret and understand our experimental data in neuroscience,” says Richards.
Image Credit: christitzeimaging.com / Shutterstock.com Continue reading

Posted in Human Robots