Videos & Podcasts
Brains@Bay – An Exploration of Grid Cells in Machine Learning
In this Brains@Bay meetup, we are focusing on grid cells and how they act as an inspiration for machine learning architectures. We are thrilled to have Marcus Lewis (Numenta), James Whittington (U of Oxford), and Kimberly Stachenfeld (DeepMind) present their exciting work on grid cells.
Brains@Bay – A Thousand Brains: a fireside chat with Jeff Hawkins
In this special Brains@Bay meetup, Lucas talked to Jeff Hawkins about his new book, A Thousand Brains. They covered the main aspects of the theory, what it represents for neuroscience and machine learning and how to incorporate these breakthrough ideas into our existing learning algorithms.
NICE 2021: From Brains to Silicon – Applying Lessons from Neuroscience to Machine Learning
Jeff Hawkins and Subutai Ahmad presents a keynote “From Brains to Silicon — Applying lessons from neuroscience to machine learning.” This keynote was presented on March 17th, 2021 at the virtual NICE workshop.
Jeff Hawkins: How The Brain Uses Reference Frames to Model the World, Why AI Needs to do the Same | NAISys 2020
Jeff Hawkins presents a talk on “How the Brain Uses Reference Frames to Model the World, Why AI Needs to do the Same.” This presentation was presented on November 10, 2020 at the virtual From Neuroscience to Artificially Intelligent Systems (NAISys) conference. In this talk, he gives an overview of The Thousand Brains Theory and discusses how machine intelligence can benefit from working on the same principles as the neocortex.
Brains@Bay – Alternatives to Backpropagation in Neural Networks
In this meetup, we discuss alternatives to backpropagation in neural networks. We invited Prof. Rafal Bogacz (Oxford), Sindy Löwe (Amsterdam) and Jack Kendall (RAIN Neuromorphics) to present their views and latest research on the topic from a neuroscience and machine learning perspective.
Technology Validation: Sparsity Enables 50x Performance Acceleration Deep Learning Networks
This video walks through the results of Numenta’s technology demonstration that shows 50x performance improvements on inference tasks in deep learning networks without any loss in accuracy.