We are a team of scientists and engineers applying neuroscience principles to machine intelligence research. Our neuroscience research code is publicly disclosed and available in open source.
Numenta has developed a major theory of intelligence and how the brain works called The Thousand Brains Theory of Intelligence, and we’re now exploring how to incorporate key principles of the theory to the field of machine intelligence.
We are one of the few teams that has developed large scale theories of the brain that are biologically constrained, testable, and implemented in software. We believe The Thousand Brains Theory will be foundational to the creation of truly intelligent systems.
Over the past decade, machine learning and AI have succeeded at performing many tasks that were unimaginable earlier. Problems such as identifying a cat in an image or recognizing someone’s speech are now routine in our lives. Yet, the way these technologies accomplish the tasks is fundamentally different than how our brain accomplishes the same tasks. For example, a machine learning system that recognizes a cat may be trained with over a million labeled training images in order to reliably identify a cat, whereas a human child learns about a cat with just a handful of examples. Moreover, that child knows that the cat may purr, the cat may scratch and the cat can jump high, whereas all the machine knows is what a cat looks like. The machine doesn’t understand cat; the child does.
The limitations faced by today’s AI systems are generally agreed in the machine learning community. Such systems require enormous time and resource to train, are brittle to noise, cannot learn continuously, and do not generalize but rather accomplish narrow, specific goals. We are still a long way from a robot performing tasks that a child can handle easily.
We do not believe it is possible to overcome these limitations simply by proceeding down the same path with more data and more power. A new approach is needed and we believe that approach must incorporate what we have learned from the brain.
We have a robust road map that applies the principles of neuroscience to put us on the path towards machine intelligence. In the near term, we are applying our model to existing CNN and AI models in order to enable systems that are more brain-like, such as systems that are robust to noise and can learn continuously. Long term, we will continue to build out more pieces of our model with the ultimate objective of creating intelligent sensorimotor systems that can learn, plan and act.