Sunny talks to Dr Terry Sejnowski, who has modelled the brain and used his insights to help inform AI for almost 50 years. He has been involved with neuromorphic engineering since its inception and made fundamental contributions to both neuroscience and engineering. These include demonstrating the importance of precise spike timing in the cortex, and the development of the Boltman machine. In this episode, he explains how information flows both ways between neuroscience and engineered intelligence, proposes a new way of looking at memory, and considers the Hopfield-Hinton Nobel Prize. After the interview, discussion follows with Giulia and Ralph.
Articles and Papers
- Reliability of Spike Timing in Neocortical Neurons
- Transformers and cortical waves: encoders for pulling in context across time
- Predictive sequence learning in the hippocampal formation
- ChatGPT and the Future of AI: The Deep Language Revolution
From the discussion
- A learning algorithm for Boltzmann machines
- Learning and relearning in Boltzmann machines
- Parallel networks that learn to pronounce English text
- Cormac Mccarthy: The Passenger and Stella Maris
- Cortical plasticity associated with Braille learning
Episode Credits
Producer/Writer: Sunny Bains
Co-hosts: Sunny Bains and Giulia D’Angelo
Editor: Rose Gotto
Audio Production: Taylor Marvin, Coupe Studios Music and Sound Design
Music: 3 of Diamonds by Matt Harris
For EETimes.com
This episode is produced in conjunction with EETimes. Podcast reproduced with permission.
