In 2012, computer scientist Dharmendra Modha used a powerful supercomputer to simulate the activity of more than 500 billion neurons—more, even, than the 85 billion or so neurons in the human brain. It was the culmination of almost a decade of work, as Modha progressed from simulating the brains of rodents and cats to something on the scale of humans.

The simulation consumed enormous computational resources—1.5 million processors and 1.5 petabytes (1.5 million gigabytes) of memory—and was still agonizingly slow, 1,500 times slower than the brain computes. Modha estimates that to run it in biological real time would have required 12 gigawatts of energy, about six times the maximum output capacity of the Hoover Dam. “And yet, it was just a cartoon of what the brain does,” says Modha, chief scientist for brain-inspired computing at IBM Almaden Research Center in northern California. The simulation came nowhere close to replicating the functionality of the human brain, which uses about the same amount of power as a 20-watt lightbulb…..

But the fact that computers “think” very differently than our brains do actually gives them an advantage when it comes to tasks like number crunching, while making them decidedly primitive in other areas, such as understanding human speech or learning from experience. If scientists want to simulate a brain that can match human intelligence, let alone eclipse it, they may have to start with better building blocks—computer chips inspired by our brains.

So-called neuromorphic chips replicate the architecture of the brain—that is, they talk to each other using “neuronal spikes” akin to a neuron’s action potential. This spiking behavior allows the chips to consume very little power and remain power-efficient even when tiled together into very large-scale systems. Read More

#human

Imagine picking up a glass of what you think is apple juice, only to take a sip and discover that it’s actually ginger ale. Even though you usually love the soda, this time it tastes terrible. That’s because context and internal states, including expectation, influence how all animals perceive and process sensory information, explained Alfredo Fontanini, a neurobiologist at Stony Brook University in New York. In this case, anticipating the wrong stimulus leads to a surprise, and a negative response.

But this influence isn’t limited to the quality of the perception. Among other effects, priming sensory systems to expect an input, good or bad, can also accelerate how quickly the animal then detects, identifies and reacts to it.

Years ago, Fontanini and his team found direct neural evidence of this speedup effect in the gustatory cortex, the part of the brain responsible for taste perception. Since then, they have been trying to pin down the structure of the cortical circuitry that made their results possible. Now they have. Last month, they published their findings in Nature Neuroscience: a model of a network with a specific kind of architecture that not only provides new insights into how expectation works, but also delves into broader questions about how scientists should think about perception more generally. Moreover, it falls in step with a theory of decision making that suggests the brain really does leap to conclusions, rather than building up to them. Read More

#human

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns visual concepts based on the language description of the object being referred to. Meanwhile, the learned visual concepts facilitate learning new words and parsing new sentences. We use curriculum learning to guide the searching over the large compositional space of images and language. Extensive experiments demonstrate the accuracy and efficiency of our model on learning visual concepts, word representations, and semantic parsing of sentences. Further, our method allows easy generalization to new object attributes, compositions, language concepts, scenes and questions, and even new program domains. It also empowers applications including visual question answering and bidirectional image-text retrieval. Read More

#human

Over the decades since the inception of artificial intelligence, research in the field has fallen into two main camps. The “symbolists” have sought to build intelligent machines by coding in logical rules and representations of the world. The “connectionists” have sought to construct artificial neural networks, inspired by biology, to learn about the world. The two groups have historically not gotten along.

But a new paper from MIT, IBM, and DeepMind shows the power of combining the two approaches, perhaps pointing a way forward for the field. The team, led by Josh Tenenbaum, a professor at MIT’s Center for Brains, Minds, and Machines, created a computer program called a neuro-symbolic concept learner (NS-CL) that learns about the world (albeit a simplified version) just as a child might—by looking around and talking. Read More

#human

Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision. We propose an instruction following task that requires all of the above, and which combines the practicality of simulated environments with the challenges of ambiguous, noisy real world data. StreetNav is built on top of Google Street View and provides visually accurate environments representing real places. Agents are given driving instructions which they must learn to interpret in order to successfully navigate in this environment. Since humans equipped with driving instructions can readily navigate in previously unseen cities, we set a high bar and test our trained agents for similar cognitive capabilities. Although deep reinforcement learning (RL) methods are frequently evaluated only on data that closely follow the training distribution, our dataset extends to multiple cities and has a clean train/test separation. This allows for thorough testing of generalisation ability. This paper presents the StreetNav environment and tasks, a set of novel models that establish strong baselines, and analysis of the task and the trained agents. Read More

#human

The brilliant minds at Google’s sister-company Deepmind are at it again. This time it appears they’ve developed a system by which driverless cars can navigate the same way humans do: by following directions.

;A long time ago, before the millennials were born, people had to drive in their cars without any form of GPS navigation. If you wanted to go some place new you used a paper map – they were like offline screenshots of a Google Maps image. Or someone gave you a list of directions. Read More

#human