Tag Archives: brain
#438798 This AI Thrashes the Hardest Atari Games ...
Learning from rewards seems like the simplest thing. I make coffee, I sip coffee, I’m happy. My brain registers “brewing coffee” as an action that leads to a reward.
That’s the guiding insight behind deep reinforcement learning, a family of algorithms that famously smashed most of Atari’s gaming catalog and triumphed over humans in strategy games like Go. Here, an AI “agent” explores the game, trying out different actions and registering ones that let it win.
Except it’s not that simple. “Brewing coffee” isn’t one action; it’s a series of actions spanning several minutes, where you’re only rewarded at the very end. By just tasting the final product, how do you learn to fine-tune grind coarseness, water to coffee ratio, brewing temperature, and a gazillion other factors that result in the reward—tasty, perk-me-up coffee?
That’s the problem with “sparse rewards,” which are ironically very abundant in our messy, complex world. We don’t immediately get feedback from our actions—no video-game-style dings or points for just grinding coffee beans—yet somehow we’re able to learn and perform an entire sequence of arm and hand movements while half-asleep.
This week, researchers from UberAI and OpenAI teamed up to bestow this talent on AI.
The trick is to encourage AI agents to “return” to a previous step, one that’s promising for a winning solution. The agent then keeps a record of that state, reloads it, and branches out again to intentionally explore other solutions that may have been left behind on the first go-around. Video gamers are likely familiar with this idea: live, die, reload a saved point, try something else, repeat for a perfect run-through.
The new family of algorithms, appropriately dubbed “Go-Explore,” smashed notoriously difficult Atari games like Montezuma’s Revenge that were previously unsolvable by its AI predecessors, while trouncing human performance along the way.
It’s not just games and digital fun. In a computer simulation of a robotic arm, the team found that installing Go-Explore as its “brain” allowed it to solve a challenging series of actions when given very sparse rewards. Because the overarching idea is so simple, the authors say, it can be adapted and expanded to other real-world problems, such as drug design or language learning.
Growing Pains
How do you reward an algorithm?
Rewards are very hard to craft, the authors say. Take the problem of asking a robot to go to a fridge. A sparse reward will only give the robot “happy points” if it reaches its destination, which is similar to asking a baby, with no concept of space and danger, to crawl through a potential minefield of toys and other obstacles towards a fridge.
“In practice, reinforcement learning works very well, if you have very rich feedback, if you can tell, ‘hey, this move is good, that move is bad, this move is good, that move is bad,’” said study author Joost Huinzinga. However, in situations that offer very little feedback, “rewards can intentionally lead to a dead end. Randomly exploring the space just doesn’t cut it.”
The other extreme is providing denser rewards. In the same robot-to-fridge example, you could frequently reward the bot as it goes along its journey, essentially helping “map out” the exact recipe to success. But that’s troubling as well. Over-holding an AI’s hand could result in an extremely rigid robot that ignores new additions to its path—a pet, for example—leading to dangerous situations. It’s a deceptive AI solution that seems effective in a simple environment, but crashes in the real world.
What we need are AI agents that can tackle both problems, the team said.
Intelligent Exploration
The key is to return to the past.
For AI, motivation usually comes from “exploring new or unusual situations,” said Huizinga. It’s efficient, but comes with significant downsides. For one, the AI agent could prematurely stop going back to promising areas because it thinks it had already found a good solution. For another, it could simply forget a previous decision point because of the mechanics of how it probes the next step in a problem.
For a complex task, the end result is an AI that randomly stumbles around towards a solution while ignoring potentially better ones.
“Detaching from a place that was previously visited after collecting a reward doesn’t work in difficult games, because you might leave out important clues,” Huinzinga explained.
Go-Explore solves these problems with a simple principle: first return, then explore. In essence, the algorithm saves different approaches it previously tried and loads promising save points—once more likely to lead to victory—to explore further.
Digging a bit deeper, the AI stores screen caps from a game. It then analyzes saved points and groups images that look alike as a potential promising “save point” to return to. Rinse and repeat. The AI tries to maximize its final score in the game, and updates its save points when it achieves a new record score. Because Atari doesn’t usually allow people to revisit any random point, the team used an emulator, which is a kind of software that mimics the Atari system but with custom abilities such as saving and reloading at any time.
The trick worked like magic. When pitted against 55 Atari games in the OpenAI gym, now commonly used to benchmark reinforcement learning algorithms, Go-Explore knocked out state-of-the-art AI competitors over 85 percent of the time.
It also crushed games previously unbeatable by AI. Montezuma’s Revenge, for example, requires you to move Pedro, the blocky protagonist, through a labyrinth of underground temples while evading obstacles such as traps and enemies and gathering jewels. One bad jump could derail the path to the next level. It’s a perfect example of sparse rewards: you need a series of good actions to get to the reward—advancing onward.
Go-Explore didn’t just beat all levels of the game, a first for AI. It also scored higher than any previous record for reinforcement learning algorithms at lower levels while toppling the human world record.
Outside a gaming environment, Go-Explore was also able to boost the performance of a simulated robot arm. While it’s easy for humans to follow high-level guidance like “put the cup on this shelf in a cupboard,” robots often need explicit training—from grasping the cup to recognizing a cupboard, moving towards it while avoiding obstacles, and learning motions to not smash the cup when putting it down.
Here, similar to the real world, the digital robot arm was only rewarded when it placed the cup onto the correct shelf, out of four possible shelves. When pitted against another algorithm, Go-Explore quickly figured out the movements needed to place the cup, while its competitor struggled with even reliably picking the cup up.
Combining Forces
By itself, the “first return, then explore” idea behind Go-Explore is already powerful. The team thinks it can do even better.
One idea is to change the mechanics of save points. Rather than reloading saved states through the emulator, it’s possible to train a neural network to do the same, without needing to relaunch a saved state. It’s a potential way to make the AI even smarter, the team said, because it can “learn” to overcome one obstacle once, instead of solving the same problem again and again. The downside? It’s much more computationally intensive.
Another idea is to combine Go-Explore with an alternative form of learning, called “imitation learning.” Here, an AI observes human behavior and mimics it through a series of actions. Combined with Go-Explore, said study author Adrien Ecoffet, this could make more robust robots capable of handling all the complexity and messiness in the real world.
To the team, the implications go far beyond Go-Explore. The concept of “first return, then explore” seems to be especially powerful, suggesting “it may be a fundamental feature of learning in general.” The team said, “Harnessing these insights…may be essential…to create generally intelligent agents.”
Image Credit: Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, and Jeff Clune Continue reading
Posted in Human Robots
#438078 How modern robots are developed
Today, neuroscience and robotics are developing hand in hand. Mikhail Lebedev, Academic Supervisor at HSE University's Centre for Bioelectric Interfaces, spoke about how studying the brain inspires the development of robots. Continue reading
Posted in Human Robots
#437978 How Mirroring the Architecture of the ...
While AI can carry out some impressive feats when trained on millions of data points, the human brain can often learn from a tiny number of examples. New research shows that borrowing architectural principles from the brain can help AI get closer to our visual prowess.
The prevailing wisdom in deep learning research is that the more data you throw at an algorithm, the better it will learn. And in the era of Big Data, that’s easier than ever, particularly for the large data-centric tech companies carrying out a lot of the cutting-edge AI research.
Today’s largest deep learning models, like OpenAI’s GPT-3 and Google’s BERT, are trained on billions of data points, and even more modest models require large amounts of data. Collecting these datasets and investing the computational resources to crunch through them is a major bottleneck, particularly for less well-resourced academic labs.
It also means today’s AI is far less flexible than natural intelligence. While a human only needs to see a handful of examples of an animal, a tool, or some other category of object to be able pick it out again, most AI need to be trained on many examples of an object in order to be able to recognize it.
There is an active sub-discipline of AI research aimed at what is known as “one-shot” or “few-shot” learning, where algorithms are designed to be able to learn from very few examples. But these approaches are still largely experimental, and they can’t come close to matching the fastest learner we know—the human brain.
This prompted a pair of neuroscientists to see if they could design an AI that could learn from few data points by borrowing principles from how we think the brain solves this problem. In a paper in Frontiers in Computational Neuroscience, they explained that the approach significantly boosts AI’s ability to learn new visual concepts from few examples.
“Our model provides a biologically plausible way for artificial neural networks to learn new visual concepts from a small number of examples,” Maximilian Riesenhuber, from Georgetown University Medical Center, said in a press release. “We can get computers to learn much better from few examples by leveraging prior learning in a way that we think mirrors what the brain is doing.”
Several decades of neuroscience research suggest that the brain’s ability to learn so quickly depends on its ability to use prior knowledge to understand new concepts based on little data. When it comes to visual understanding, this can rely on similarities of shape, structure, or color, but the brain can also leverage abstract visual concepts thought to be encoded in a brain region called the anterior temporal lobe (ATL).
“It is like saying that a platypus looks a bit like a duck, a beaver, and a sea otter,” said paper co-author Joshua Rule, from the University of California Berkeley.
The researchers decided to try and recreate this capability by using similar high-level concepts learned by an AI to help it quickly learn previously unseen categories of images.
Deep learning algorithms work by getting layers of artificial neurons to learn increasingly complex features of an image or other data type, which are then used to categorize new data. For instance, early layers will look for simple features like edges, while later ones might look for more complex ones like noses, faces, or even more high-level characteristics.
First they trained the AI on 2.5 million images across 2,000 different categories from the popular ImageNet dataset. They then extracted features from various layers of the network, including the very last layer before the output layer. They refer to these as “conceptual features” because they are the highest-level features learned, and most similar to the abstract concepts that might be encoded in the ATL.
They then used these different sets of features to train the AI to learn new concepts based on 2, 4, 8, 16, 32, 64, and 128 examples. They found that the AI that used the conceptual features yielded much better performance than ones trained using lower-level features on lower numbers of examples, but the gap shrunk as they were fed more training examples.
While the researchers admit the challenge they set their AI was relatively simple and only covers one aspect of the complex process of visual reasoning, they said that using a biologically plausible approach to solving the few-shot problem opens up promising new avenues in both neuroscience and AI.
“Our findings not only suggest techniques that could help computers learn more quickly and efficiently, they can also lead to improved neuroscience experiments aimed at understanding how people learn so quickly, which is not yet well understood,” Riesenhuber said.
As the researchers note, the human visual system is still the gold standard when it comes to understanding the world around us. Borrowing from its design principles might turn out to be a profitable direction for future research.
Image Credit: Gerd Altmann from Pixabay Continue reading
Posted in Human Robots
#437974 China Wants to Be the World’s AI ...
China’s star has been steadily rising for decades. Besides slashing extreme poverty rates from 88 percent to under 2 percent in just 30 years, the country has become a global powerhouse in manufacturing and technology. Its pace of growth may slow due to an aging population, but China is nonetheless one of the world’s biggest players in multiple cutting-edge tech fields.
One of these fields, and perhaps the most significant, is artificial intelligence. The Chinese government announced a plan in 2017 to become the world leader in AI by 2030, and has since poured billions of dollars into AI projects and research across academia, government, and private industry. The government’s venture capital fund is investing over $30 billion in AI; the northeastern city of Tianjin budgeted $16 billion for advancing AI; and a $2 billion AI research park is being built in Beijing.
On top of these huge investments, the government and private companies in China have access to an unprecedented quantity of data, on everything from citizens’ health to their smartphone use. WeChat, a multi-functional app where people can chat, date, send payments, hail rides, read news, and more, gives the CCP full access to user data upon request; as one BBC journalist put it, WeChat “was ahead of the game on the global stage and it has found its way into all corners of people’s existence. It could deliver to the Communist Party a life map of pretty much everybody in this country, citizens and foreigners alike.” And that’s just one (albeit big) source of data.
Many believe these factors are giving China a serious leg up in AI development, even providing enough of a boost that its progress will surpass that of the US.
But there’s more to AI than data, and there’s more to progress than investing billions of dollars. Analyzing China’s potential to become a world leader in AI—or in any technology that requires consistent innovation—from multiple angles provides a more nuanced picture of its strengths and limitations. In a June 2020 article in Foreign Affairs, Oxford fellows Carl Benedikt Frey and Michael Osborne argued that China’s big advantages may not actually be that advantageous in the long run—and its limitations may be very limiting.
Moving the AI Needle
To get an idea of who’s likely to take the lead in AI, it could help to first consider how the technology will advance beyond its current state.
To put it plainly, AI is somewhat stuck at the moment. Algorithms and neural networks continue to achieve new and impressive feats—like DeepMind’s AlphaFold accurately predicting protein structures or OpenAI’s GPT-3 writing convincing articles based on short prompts—but for the most part these systems’ capabilities are still defined as narrow intelligence: completing a specific task for which the system was painstakingly trained on loads of data.
(It’s worth noting here that some have speculated OpenAI’s GPT-3 may be an exception, the first example of machine intelligence that, while not “general,” has surpassed the definition of “narrow”; the algorithm was trained to write text, but ended up being able to translate between languages, write code, autocomplete images, do math, and perform other language-related tasks it wasn’t specifically trained for. However, all of GPT-3’s capabilities are limited to skills it learned in the language domain, whether spoken, written, or programming language).
Both AlphaFold’s and GPT-3’s success was due largely to the massive datasets they were trained on; no revolutionary new training methods or architectures were involved. If all it was going to take to advance AI was a continuation or scaling-up of this paradigm—more input data yields increased capability—China could well have an advantage.
But one of the biggest hurdles AI needs to clear to advance in leaps and bounds rather than baby steps is precisely this reliance on extensive, task-specific data. Other significant challenges include the technology’s fast approach to the limits of current computing power and its immense energy consumption.
Thus, while China’s trove of data may give it an advantage now, it may not be much of a long-term foothold on the climb to AI dominance. It’s useful for building products that incorporate or rely on today’s AI, but not for pushing the needle on how artificially intelligent systems learn. WeChat data on users’ spending habits, for example, would be valuable in building an AI that helps people save money or suggests items they might want to purchase. It will enable (and already has enabled) highly tailored products that will earn their creators and the companies that use them a lot of money.
But data quantity isn’t what’s going to advance AI. As Frey and Osborne put it, “Data efficiency is the holy grail of further progress in artificial intelligence.”
To that end, research teams in academia and private industry are working on ways to make AI less data-hungry. New training methods like one-shot learning and less-than-one-shot learning have begun to emerge, along with myriad efforts to make AI that learns more like the human brain.
While not insignificant, these advancements still fall into the “baby steps” category. No one knows how AI is going to progress beyond these small steps—and that uncertainty, in Frey and Osborne’s opinion, is a major speed bump on China’s fast-track to AI dominance.
How Innovation Happens
A lot of great inventions have happened by accident, and some of the world’s most successful companies started in garages, dorm rooms, or similarly low-budget, nondescript circumstances (including Google, Facebook, Amazon, and Apple, to name a few). Innovation, the authors point out, often happens “through serendipity and recombination, as inventors and entrepreneurs interact and exchange ideas.”
Frey and Osborne argue that although China has great reserves of talent and a history of building on technologies conceived elsewhere, it doesn’t yet have a glowing track record in terms of innovation. They note that of the 100 most-cited patents from 2003 to present, none came from China. Giants Tencent, Alibaba, and Baidu are all wildly successful in the Chinese market, but they’re rooted in technologies or business models that came out of the US and were tweaked for the Chinese population.
“The most innovative societies have always been those that allowed people to pursue controversial ideas,” Frey and Osborne write. China’s heavy censorship of the internet and surveillance of citizens don’t quite encourage the pursuit of controversial ideas. The country’s social credit system rewards people who follow the rules and punishes those who step out of line. Frey adds that top-down execution of problem-solving is effective when the problem at hand is clearly defined—and the next big leaps in AI are not.
It’s debatable how strongly a culture of social conformism can impact technological innovation, and of course there can be exceptions. But a relevant historical example is the Soviet Union, which, despite heavy investment in science and technology that briefly rivaled the US in fields like nuclear energy and space exploration, ended up lagging far behind primarily due to political and cultural factors.
Similarly, China’s focus on computer science in its education system could give it an edge—but, as Frey told me in an email, “The best students are not necessarily the best researchers. Being a good researcher also requires coming up with new ideas.”
Winner Take All?
Beyond the question of whether China will achieve AI dominance is the issue of how it will use the powerful technology. Several of the ways China has already implemented AI could be considered morally questionable, from facial recognition systems used aggressively against ethnic minorities to smart glasses for policemen that can pull up information about whoever the wearer looks at.
This isn’t to say the US would use AI for purely ethical purposes. The military’s Project Maven, for example, used artificially intelligent algorithms to identify insurgent targets in Iraq and Syria, and American law enforcement agencies are also using (mostly unregulated) facial recognition systems.
It’s conceivable that “dominance” in AI won’t go to one country; each nation could meet milestones in different ways, or meet different milestones. Researchers from both countries, at least in the academic sphere, could (and likely will) continue to collaborate and share their work, as they’ve done on many projects to date.
If one country does take the lead, it will certainly see some major advantages as a result. Brookings Institute fellow Indermit Gill goes so far as to say that whoever leads in AI in 2030 will “rule the world” until 2100. But Gill points out that in addition to considering each country’s strengths, we should consider how willing they are to improve upon their weaknesses.
While China leads in investment and the US in innovation, both nations are grappling with huge economic inequalities that could negatively impact technological uptake. “Attitudes toward the social change that accompanies new technologies matter as much as the technologies, pointing to the need for complementary policies that shape the economy and society,” Gill writes.
Will China’s leadership be willing to relax its grip to foster innovation? Will the US business environment be enough to compete with China’s data, investment, and education advantages? And can both countries find a way to distribute technology’s economic benefits more equitably?
Time will tell, but it seems we’ve got our work cut out for us—and China does too.
Image Credit: Adam Birkett on Unsplash Continue reading
Posted in Human Robots
#437957 Meet Assembloids, Mini Human Brains With ...
It’s not often that a twitching, snowman-shaped blob of 3D human tissue makes someone’s day.
But when Dr. Sergiu Pasca at Stanford University witnessed the tiny movement, he knew his lab had achieved something special. You see, the blob was evolved from three lab-grown chunks of human tissue: a mini-brain, mini-spinal cord, and mini-muscle. Each individual component, churned to eerie humanoid perfection inside bubbling incubators, is already a work of scientific genius. But Pasca took the extra step, marinating the three components together inside a soup of nutrients.
The result was a bizarre, Lego-like human tissue that replicates the basic circuits behind how we decide to move. Without external prompting, when churned together like ice cream, the three ingredients physically linked up into a fully functional circuit. The 3D mini-brain, through the information highway formed by the artificial spinal cord, was able to make the lab-grown muscle twitch on demand.
In other words, if you think isolated mini-brains—known formally as brain organoids—floating in a jar is creepy, upgrade your nightmares. The next big thing in probing the brain is assembloids—free-floating brain circuits—that now combine brain tissue with an external output.
The end goal isn’t to freak people out. Rather, it’s to recapitulate our nervous system, from input to output, inside the controlled environment of a Petri dish. An autonomous, living brain-spinal cord-muscle entity is an invaluable model for figuring out how our own brains direct the intricate muscle movements that allow us stay upright, walk, or type on a keyboard.
It’s the nexus toward more dexterous brain-machine interfaces, and a model to understand when brain-muscle connections fail—as in devastating conditions like Lou Gehrig’s disease or Parkinson’s, where people slowly lose muscle control due to the gradual death of neurons that control muscle function. Assembloids are a sort of “mini-me,” a workaround for testing potential treatments on a simple “replica” of a person rather than directly on a human.
From Organoids to Assembloids
The miniature snippet of the human nervous system has been a long time in the making.
It all started in 2014, when Dr. Madeleine Lancaster, then a post-doc at Stanford, grew a shockingly intricate 3D replica of human brain tissue inside a whirling incubator. Revolutionarily different than standard cell cultures, which grind up brain tissue to reconstruct as a flat network of cells, Lancaster’s 3D brain organoids were incredibly sophisticated in their recapitulation of the human brain during development. Subsequent studies further solidified their similarity to the developing brain of a fetus—not just in terms of neuron types, but also their connections and structure.
With the finding that these mini-brains sparked with electrical activity, bioethicists increasingly raised red flags that the blobs of human brain tissue—no larger than the size of a pea at most—could harbor the potential to develop a sense of awareness if further matured and with external input and output.
Despite these concerns, brain organoids became an instant hit. Because they’re made of human tissue—often taken from actual human patients and converted into stem-cell-like states—organoids harbor the same genetic makeup as their donors. This makes it possible to study perplexing conditions such as autism, schizophrenia, or other brain disorders in a dish. What’s more, because they’re grown in the lab, it’s possible to genetically edit the mini-brains to test potential genetic culprits in the search for a cure.
Yet mini-brains had an Achilles’ heel: not all were made the same. Rather, depending on the region of the brain that was reverse engineered, the cells had to be persuaded by different cocktails of chemical soups and maintained in isolation. It was a stark contrast to our own developing brains, where regions are connected through highways of neural networks and work in tandem.
Pasca faced the problem head-on. Betting on the brain’s self-assembling capacity, his team hypothesized that it might be possible to grow different mini-brains, each reflecting a different brain region, and have them fuse together into a synchronized band of neuron circuits to process information. Last year, his idea paid off.
In one mind-blowing study, his team grew two separate portions of the brain into blobs, one representing the cortex, the other a deeper part of the brain known to control reward and movement, called the striatum. Shockingly, when put together, the two blobs of human brain tissue fused into a functional couple, automatically establishing neural highways that resulted in one of the most sophisticated recapitulations of a human brain. Pasca crowned this tissue engineering crème-de-la-crème “assembloids,” a portmanteau between “assemble” and “organoids.”
“We have demonstrated that regionalized brain spheroids can be put together to form fused structures called brain assembloids,” said Pasca at the time.” [They] can then be used to investigate developmental processes that were previously inaccessible.”
And if that’s possible for wiring up a lab-grown brain, why wouldn’t it work for larger neural circuits?
Assembloids, Assemble
The new study is the fruition of that idea.
The team started with human skin cells, scraped off of eight healthy people, and transformed them into a stem-cell-like state, called iPSCs. These cells have long been touted as the breakthrough for personalized medical treatment, before each reflects the genetic makeup of its original host.
Using two separate cocktails, the team then generated mini-brains and mini-spinal cords using these iPSCs. The two components were placed together “in close proximity” for three days inside a lab incubator, gently floating around each other in an intricate dance. To the team’s surprise, under the microscope using tracers that glow in the dark, they saw highways of branches extending from one organoid to the other like arms in a tight embrace. When stimulated with electricity, the links fired up, suggesting that the connections weren’t just for show—they’re capable of transmitting information.
“We made the parts,” said Pasca, “but they knew how to put themselves together.”
Then came the ménage à trois. Once the mini-brain and spinal cord formed their double-decker ice cream scoop, the team overlaid them onto a layer of muscle cells—cultured separately into a human-like muscular structure. The end result was a somewhat bizarre and silly-looking snowman, made of three oddly-shaped spherical balls.
Yet against all odds, the brain-spinal cord assembly reached out to the lab-grown muscle. Using a variety of tools, including measuring muscle contraction, the team found that this utterly Frankenstein-like snowman was able to make the muscle component contract—in a way similar to how our muscles twitch when needed.
“Skeletal muscle doesn’t usually contract on its own,” said Pasca. “Seeing that first twitch in a lab dish immediately after cortical stimulation is something that’s not soon forgotten.”
When tested for longevity, the contraption lasted for up to 10 weeks without any sort of breakdown. Far from a one-shot wonder, the isolated circuit worked even better the longer each component was connected.
Pasca isn’t the first to give mini-brains an output channel. Last year, the queen of brain organoids, Lancaster, chopped up mature mini-brains into slices, which were then linked to muscle tissue through a cultured spinal cord. Assembloids are a step up, showing that it’s possible to automatically sew multiple nerve-linked structures together, such as brain and muscle, sans slicing.
The question is what happens when these assembloids become more sophisticated, edging ever closer to the inherent wiring that powers our movements. Pasca’s study targets outputs, but what about inputs? Can we wire input channels, such as retinal cells, to mini-brains that have a rudimentary visual cortex to process those examples? Learning, after all, depends on examples of our world, which are processed inside computational circuits and delivered as outputs—potentially, muscle contractions.
To be clear, few would argue that today’s mini-brains are capable of any sort of consciousness or awareness. But as mini-brains get increasingly more sophisticated, at what point can we consider them a sort of AI, capable of computation or even something that mimics thought? We don’t yet have an answer—but the debates are on.
Image Credit: christitzeimaging.com / Shutterstock.com Continue reading
Posted in Human Robots