Tag Archives: experiment
According to some scientists, humans really do have a sixth sense. There’s nothing supernatural about it: the sense of proprioception tells you about the relative positions of your limbs and the rest of your body. Close your eyes, block out all sound, and you can still use this internal “map” of your external body to locate your muscles and body parts – you have an innate sense of the distances between them, and the perception of how they’re moving, above and beyond your sense of touch.
This sense is invaluable for allowing us to coordinate our movements. In humans, the brain integrates senses including touch, heat, and the tension in muscle spindles to allow us to build up this map.
Replicating this complex sense has posed a great challenge for roboticists. We can imagine simulating the sense of sight with cameras, sound with microphones, or touch with pressure-pads. Robots with chemical sensors could be far more accurate than us in smell and taste, but building in proprioception, the robot’s sense of itself and its body, is far more difficult, and is a large part of why humanoid robots are so tricky to get right.
Simultaneous localization and mapping (SLAM) software allows robots to use their own senses to build up a picture of their surroundings and environment, but they’d need a keen sense of the position of their own bodies to interact with it. If something unexpected happens, or in dark environments where primary senses are not available, robots can struggle to keep track of their own position and orientation. For human-robot interaction, wearable robotics, and delicate applications like surgery, tiny differences can be extremely important.
In the case of hard robotics, this is generally solved by using a series of strain and pressure sensors in each joint, which allow the robot to determine how its limbs are positioned. That works fine for rigid robots with a limited number of joints, but for softer, more flexible robots, this information is limited. Roboticists are faced with a dilemma: a vast, complex array of sensors for every degree of freedom in the robot’s movement, or limited skill in proprioception?
New techniques, often involving new arrays of sensory material and machine-learning algorithms to fill in the gaps, are starting to tackle this problem. Take the work of Thomas George Thuruthel and colleagues in Pisa and San Diego, who draw inspiration from the proprioception of humans. In a new paper in Science Robotics, they describe the use of soft sensors distributed through a robotic finger at random. This placement is much like the constant adaptation of sensors in humans and animals, rather than relying on feedback from a limited number of positions.
The sensors allow the soft robot to react to touch and pressure in many different locations, forming a map of itself as it contorts into complicated positions. The machine-learning algorithm serves to interpret the signals from the randomly-distributed sensors: as the finger moves around, it’s observed by a motion capture system. After training the robot’s neural network, it can associate the feedback from the sensors with the position of the finger detected in the motion-capture system, which can then be discarded. The robot observes its own motions to understand the shapes that its soft body can take, and translate them into the language of these soft sensors.
“The advantages of our approach are the ability to predict complex motions and forces that the soft robot experiences (which is difficult with traditional methods) and the fact that it can be applied to multiple types of actuators and sensors,” said Michael Tolley of the University of California San Diego. “Our method also includes redundant sensors, which improves the overall robustness of our predictions.”
The use of machine learning lets the roboticists come up with a reliable model for this complex, non-linear system of motions for the actuators, something difficult to do by directly calculating the expected motion of the soft-bot. It also resembles the human system of proprioception, built on redundant sensors that change and shift in position as we age.
In Search of a Perfect Arm
Another approach to training robots in using their bodies comes from Robert Kwiatkowski and Hod Lipson of Columbia University in New York. In their paper “Task-agnostic self-modeling machines,” also recently published in Science Robotics, they describe a new type of robotic arm.
Robotic arms and hands are getting increasingly dexterous, but training them to grasp a large array of objects and perform many different tasks can be an arduous process. It’s also an extremely valuable skill to get right: Amazon is highly interested in the perfect robot arm. Google hooked together an array of over a dozen robot arms so that they could share information about grasping new objects, in part to cut down on training time.
Individually training a robot arm to perform every individual task takes time and reduces the adaptability of your robot: either you need an ML algorithm with a huge dataset of experiences, or, even worse, you need to hard-code thousands of different motions. Kwiatkowski and Lipson attempt to overcome this by developing a robotic system that has a “strong sense of self”: a model of its own size, shape, and motions.
They do this using deep machine learning. The robot begins with no prior knowledge of its own shape or the underlying physics of its motion. It then repeats a series of a thousand random trajectories, recording the motion of its arm. Kwiatkowski and Lipson compare this to a baby in the first year of life observing the motions of its own hands and limbs, fascinated by picking up and manipulating objects.
Again, once the robot has trained itself to interpret these signals and build up a robust model of its own body, it’s ready for the next stage. Using that deep-learning algorithm, the researchers then ask the robot to design strategies to accomplish simple pick-up and place and handwriting tasks. Rather than laboriously and narrowly training itself for each individual task, limiting its abilities to a very narrow set of circumstances, the robot can now strategize how to use its arm for a much wider range of situations, with no additional task-specific training.
In a further experiment, the researchers replaced part of the arm with a “deformed” component, intended to simulate what might happen if the robot was damaged. The robot can then detect that something’s up and “reconfigure” itself, reconstructing its self-model by going through the training exercises once again; it was then able to perform the same tasks with only a small reduction in accuracy.
Machine learning techniques are opening up the field of robotics in ways we’ve never seen before. Combining them with our understanding of how humans and other animals are able to sense and interact with the world around us is bringing robotics closer and closer to becoming truly flexible and adaptable, and, eventually, omnipresent.
But before they can get out and shape the world, as these studies show, they will need to understand themselves.
Image Credit: jumbojan / Shutterstock.com Continue reading
Scarcely a day goes by without another headline about neural networks: some new task that deep learning algorithms can excel at, approaching or even surpassing human competence. As the application of this approach to computer vision has continued to improve, with algorithms capable of specialized recognition tasks like those found in medicine, the software is getting closer to widespread commercial use—for example, in self-driving cars. Our ability to recognize patterns is a huge part of human intelligence: if this can be done faster by machines, the consequences will be profound.
Yet, as ever with algorithms, there are deep concerns about their reliability, especially when we don’t know precisely how they work. State-of-the-art neural networks will confidently—and incorrectly—classify images that look like television static or abstract art as real-world objects like school-buses or armadillos. Specific algorithms could be targeted by “adversarial examples,” where adding an imperceptible amount of noise to an image can cause an algorithm to completely mistake one object for another. Machine learning experts enjoy constructing these images to trick advanced software, but if a self-driving car could be fooled by a few stickers, it might not be so fun for the passengers.
These difficulties are hard to smooth out in large part because we don’t have a great intuition for how these neural networks “see” and “recognize” objects. The main insight analyzing a trained network itself can give us is a series of statistical weights, associating certain groups of points with certain objects: this can be very difficult to interpret.
Now, new research from UCLA, published in the journal PLOS Computational Biology, is testing neural networks to understand the limits of their vision and the differences between computer vision and human vision. Nicholas Baker, Hongjing Lu, and Philip J. Kellman of UCLA, alongside Gennady Erlikhman of the University of Nevada, tested a deep convolutional neural network called VGG-19. This is state-of-the-art technology that is already outperforming humans on standardized tests like the ImageNet Large Scale Visual Recognition Challenge.
They found that, while humans tend to classify objects based on their overall (global) shape, deep neural networks are far more sensitive to the textures of objects, including local color gradients and the distribution of points on the object. This result helps explain why neural networks in image recognition make mistakes that no human ever would—and could allow for better designs in the future.
In the first experiment, a neural network was trained to sort images into 1 of 1,000 different categories. It was then presented with silhouettes of these images: all of the local information was lost, while only the outline of the object remained. Ordinarily, the trained neural net was capable of recognizing these objects, assigning more than 90% probability to the correct classification. Studying silhouettes, this dropped to 10%. While human observers could nearly always produce correct shape labels, the neural networks appeared almost insensitive to the overall shape of the images. On average, the correct object was ranked as the 209th most likely solution by the neural network, even though the overall shapes were an exact match.
A particularly striking example arose when they tried to get the neural networks to classify glass figurines of objects they could already recognize. While you or I might find it easy to identify a glass model of an otter or a polar bear, the neural network classified them as “oxygen mask” and “can opener” respectively. By presenting glass figurines, where the texture information that neural networks relied on for classifying objects is lost, the neural network was unable to recognize the objects by shape alone. The neural network was similarly hopeless at classifying objects based on drawings of their outline.
If you got one of these right, you’re better than state-of-the-art image recognition software. Image Credit: Nicholas Baker, Hongjing Lu, Gennady Erlikhman, Philip J. Kelman. “Deep convolutional networks do not classify based on global object shape.” Plos Computational Biology. 12/7/18. / CC BY 4.0
When the neural network was explicitly trained to recognize object silhouettes—given no information in the training data aside from the object outlines—the researchers found that slight distortions or “ripples” to the contour of the image were again enough to fool the AI, while humans paid them no mind.
The fact that neural networks seem to be insensitive to the overall shape of an object—relying instead on statistical similarities between local distributions of points—suggests a further experiment. What if you scrambled the images so that the overall shape was lost but local features were preserved? It turns out that the neural networks are far better and faster at recognizing scrambled versions of objects than outlines, even when humans struggle. Students could classify only 37% of the scrambled objects, while the neural network succeeded 83% of the time.
Humans vastly outperform machines at classifying object (a) as a bear, while the machine learning algorithm has few problems classifying the bear in figure (b). Image Credit: Nicholas Baker, Hongjing Lu, Gennady Erlikhman, Philip J. Kelman. “Deep convolutional networks do not classify based on global object shape.” Plos Computational Biology. 12/7/18. / CC BY 4.0
“This study shows these systems get the right answer in the images they were trained on without considering shape,” Kellman said. “For humans, overall shape is primary for object recognition, and identifying images by overall shape doesn’t seem to be in these deep learning systems at all.”
Naively, one might expect that—as the many layers of a neural network are modeled on connections between neurons in the brain and resemble the visual cortex specifically—the way computer vision operates must necessarily be similar to human vision. But this kind of research shows that, while the fundamental architecture might resemble that of the human brain, the resulting “mind” operates very differently.
Researchers can, increasingly, observe how the “neurons” in neural networks light up when exposed to stimuli and compare it to how biological systems respond to the same stimuli. Perhaps someday it might be possible to use these comparisons to understand how neural networks are “thinking” and how those responses differ from humans.
But, as yet, it takes a more experimental psychology to probe how neural networks and artificial intelligence algorithms perceive the world. The tests employed against the neural network are closer to how scientists might try to understand the senses of an animal or the developing brain of a young child rather than a piece of software.
By combining this experimental psychology with new neural network designs or error-correction techniques, it may be possible to make them even more reliable. Yet this research illustrates just how much we still don’t understand about the algorithms we’re creating and using: how they tick, how they make decisions, and how they’re different from us. As they play an ever-greater role in society, understanding the psychology of neural networks will be crucial if we want to use them wisely and effectively—and not end up missing the woods for the trees.
Image Credit: Irvan Pratama / Shutterstock.com Continue reading
2018 was bonkers for science.
From a woman who gave birth using a transplanted uterus, to the infamous CRISPR baby scandal, to forensics adopting consumer-based genealogy test kits to track down criminals, last year was a factory churning out scientific “whoa” stories with consequences for years to come.
With CRISPR still in the headlines, Britain ready to bid Europe au revoir, and multiple scientific endeavors taking off, 2019 is shaping up to be just as tumultuous.
Here are the science and health stories that may blow up in the new year. But first, a note of caveat: predicting the future is tough. Forecasting is the lovechild between statistics and (a good deal of) intuition, and entire disciplines have been dedicated to the endeavor. But January is the perfect time to gaze into the crystal ball for wisps of insight into the year to come. Last year we predicted the widespread approval of gene therapy products—on the most part, we nailed it. This year we’re hedging our bets with multiple predictions.
Gene Drives Used in the Wild
The concept of gene drives scares many, for good reason. Gene drives are a step up in severity (and consequences) from CRISPR and other gene-editing tools. Even with germline editing, in which the sperm, egg, or embryos are altered, gene editing affects just one genetic line—one family—at least at the beginning, before they reproduce with the general population.
Gene drives, on the other hand, have the power to wipe out entire species.
In a nutshell, they’re little bits of DNA code that help a gene transfer from parent to child with almost 100 percent perfect probability. The “half of your DNA comes from dad, the other comes from mom” dogma? Gene drives smash that to bits.
In other words, the only time one would consider using a gene drive is to change the genetic makeup of an entire population. It sounds like the plot of a supervillain movie, but scientists have been toying around with the idea of deploying the technology—first in mosquitoes, then (potentially) in rodents.
By releasing just a handful of mutant mosquitoes that carry gene drives for infertility, for example, scientists could potentially wipe out entire populations that carry infectious scourges like malaria, dengue, or Zika. The technology is so potent—and dangerous—the US Defense Advances Research Projects Agency is shelling out $65 million to suss out how to deploy, control, counter, or even reverse the effects of tampering with ecology.
Last year, the U.N. gave a cautious go-ahead for the technology to be deployed in the wild in limited terms. Now, the first release of a genetically modified mosquito is set for testing in Burkina Faso in Africa—the first-ever field experiment involving gene drives.
The experiment will only release mosquitoes in the Anopheles genus, which are the main culprits transferring disease. As a first step, over 10,000 male mosquitoes are set for release into the wild. These dudes are genetically sterile but do not cause infertility, and will help scientists examine how they survive and disperse as a preparation for deploying gene-drive-carrying mosquitoes.
Hot on the project’s heels, the nonprofit consortium Target Malaria, backed by the Bill and Melinda Gates foundation, is engineering a gene drive called Mosq that will spread infertility across the population or kill out all female insects. Their attempt to hack the rules of inheritance—and save millions in the process—is slated for 2024.
A Universal Flu Vaccine
People often brush off flu as a mere annoyance, but the infection kills hundreds of thousands each year based on the CDC’s statistical estimates.
The flu virus is actually as difficult of a nemesis as HIV—it mutates at an extremely rapid rate, making effective vaccines almost impossible to engineer on time. Scientists currently use data to forecast the strains that will likely explode into an epidemic and urge the public to vaccinate against those predictions. That’s partly why, on average, flu vaccines only have a success rate of roughly 50 percent—not much better than a coin toss.
Tired of relying on educated guesses, scientists have been chipping away at a universal flu vaccine that targets all strains—perhaps even those we haven’t yet identified. Often referred to as the “holy grail” in epidemiology, these vaccines try to alert our immune systems to parts of a flu virus that are least variable from strain to strain.
Last November, a first universal flu vaccine developed by BiondVax entered Phase 3 clinical trials, which means it’s already been proven safe and effective in a small numbers and is now being tested in a broader population. The vaccine doesn’t rely on dead viruses, which is a common technique. Rather, it uses a small chain of amino acids—the chemical components that make up proteins—to stimulate the immune system into high alert.
With the government pouring $160 million into the research and several other universal candidates entering clinical trials, universal flu vaccines may finally experience a breakthrough this year.
In-Body Gene Editing Shows Further Promise
CRISPR and other gene editing tools headed the news last year, including both downers suggesting we already have immunity to the technology and hopeful news of it getting ready for treating inherited muscle-wasting diseases.
But what wasn’t widely broadcasted was the in-body gene editing experiments that have been rolling out with gusto. Last September, Sangamo Therapeutics in Richmond, California revealed that they had injected gene-editing enzymes into a patient in an effort to correct a genetic deficit that prevents him from breaking down complex sugars.
The effort is markedly different than the better-known CAR-T therapy, which extracts cells from the body for genetic engineering before returning them to the hosts. Rather, Sangamo’s treatment directly injects viruses carrying the edited genes into the body. So far, the procedure looks to be safe, though at the time of reporting it was too early to determine effectiveness.
This year the company hopes to finally answer whether it really worked.
If successful, it means that devastating genetic disorders could potentially be treated with just a few injections. With a gamut of new and more precise CRISPR and other gene-editing tools in the works, the list of treatable inherited diseases is likely to grow. And with the CRISPR baby scandal potentially dampening efforts at germline editing via regulations, in-body gene editing will likely receive more attention if Sangamo’s results return positive.
Neuralink and Other Brain-Machine Interfaces
Neuralink is the stuff of sci fi: tiny implanted particles into the brain could link up your biological wetware with silicon hardware and the internet.
But that’s exactly what Elon Musk’s company, founded in 2016, seeks to develop: brain-machine interfaces that could tinker with your neural circuits in an effort to treat diseases or even enhance your abilities.
Last November, Musk broke his silence on the secretive company, suggesting that he may announce something “interesting” in a few months, that’s “better than anyone thinks is possible.”
Musk’s aspiration for achieving symbiosis with artificial intelligence isn’t the driving force for all brain-machine interfaces (BMIs). In the clinics, the main push is to rehabilitate patients—those who suffer from paralysis, memory loss, or other nerve damage.
2019 may be the year that BMIs and neuromodulators cut the cord in the clinics. These devices may finally work autonomously within a malfunctioning brain, applying electrical stimulation only when necessary to reduce side effects without requiring external monitoring. Or they could allow scientists to control brains with light without needing bulky optical fibers.
Cutting the cord is just the first step to fine-tuning neurological treatments—or enhancements—to the tune of your own brain, and 2019 will keep on bringing the music.
Image Credit: angellodeco / Shutterstock.com Continue reading