In this piece originally written for Cheers Publishing, Jeff answers 3 questions about the book: the relationship between On Intelligence and A Thousand Brains, if he recommends reading both, and whether the ideas proposed in the two books have been validated.
AI and the Brain: From On Intelligence to A Thousand Brains Read More »
In our new pre-print titled “Going Beyond the Point Neuron: Active Dendrites and Sparse Representations for Continual Learning”, we investigated how to augment neural networks with properties of real neurons, specifically active dendrites and sparse representations.
Can Active Dendrites Mitigate Catastrophic Forgetting? Read More »
Are you a machine learning researcher looking for better learning algorithms? Interested in how neuroscience research can help inform the development of artificial intelligence systems? Brains@Bay may be the Meetup group for you! Brains@Bay is a meetup hosted by Numenta with the goal of bringing together experts and practitioners at the intersection of neuroscience and AI.
Brains@Bay: A Meetup on Brain-Inspired Machine Learning Algorithms Read More »
We’ve been getting a lot of questions lately as to the differences between Hinton’s GLOM model and Numenta’s Thousand Brains Theory. In this blog, we will outline the commonalities and main differences of both models at a high level.
Comparing Hinton’s GLOM Model to Numenta’s Thousand Brains Theory Read More »
In this post, Karan describes the technicalities of why neural networks do not learn continually, briefly discusses how the brain is thought to succeed at learning task after task, and finally highlights some exciting work in the machine learning community that builds on fundamental principles of neural computation to alleviate catastrophic forgetting.
Why Neural Networks Forget, and Lessons from the Brain Read More »
In our most recent peer-reviewed paper published in Frontiers in Neural Circuits, A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex, we put forward a novel theory for how the neocortex works. In this updated blog about the Thousand Brains Theory of Intelligence originally published in March 2018, Jeff Hawkins and Christy Maver describe the key insights of our theory and how it compares to the classic view of the hierarchy, as well as its implications for AI.
The Thousand Brains Theory of Intelligence Read More »
Learn how Numenta’s research provides insights into the evolution of the neocortex and discover how the neocortex’s location-based framework may be central to learning.
How Did The Neocortex Evolve? Numenta Research May Provide a Clue Read More »
The thalamus is an often overlooked part of the brain, but over the last few decades, scientists have discovered a wealth of information about it. This blog post will cover how the thalamus works and the surprising but critical role it plays in intelligent function.
The discovery of grid cells won the Nobel Prize in 2014, but do you know how they work? Working together in populations, grid cells create a cognitive map of space. Each cell responds to certain areas of space. Groups of grid cells called modules have the same projection properties onto space. Many grid cell modules working together can map a virtually infinite amount of space.
How Grid Cells Map Space Read More »
In our paper, A Theory of How Columns in the Neocortex Enable Learning the Structure of the World, we proposed that a single cortical column can learn models of complete objects through movement. Jeff Hawkins and Christy Maver explain our “Thousand Brains Model of Intelligence” and its implications for AI in this blog.
The Thousand Brains Model of Intelligence Read More »