Brain Inspired show

Brain Inspired

Summary: Neuroscience and artificial intelligence work better together. Brain inspired is a celebration and exploration of the ideas driving our progress to understand intelligence. I interview experts about their work at the interface of neuroscience, artificial intelligence, cognitive science, philosophy, psychology, and more: the symbiosis of these overlapping fields, how they inform each other, where they differ, what the past brought us, and what the future brings. Topics include computational neuroscience, supervised machine learning, unsupervised learning, reinforcement learning, deep learning, convolutional and recurrent neural networks, decision-making science, AI agents, backpropagation, credit assignment, neuroengineering, neuromorphics, emergence, philosophy of mind, consciousness, general AI, spiking neural networks, data science, and a lot more. The podcast is not produced for a general audience. Instead, it aims to educate, challenge, inspire, and hopefully entertain those interested in learning more about neuroscience and AI.

Join Now to Subscribe to this Podcast

Podcasts:

 BI 016 Ryota Kanai: Artificial Consciousness | File Type: audio/mpeg | Duration: 00:55:36

Ryota and I discuss his two goals - to implement the functions of consciousness, and to figure out how to measure whether a given system (human, AI, etc) has consciousness. We also talk about his paper implementing curiosity and empowerment as intrinsic motivation in a reinforcement learning AI agent. Plus much more.

 BI 015 Terrence Sejnowski: How to Start a Deep Learning Revolution | File Type: audio/mpeg | Duration: 00:49:34

Terry and I talk about his new book, The Deep Learning Revolution, about the past, present, and future of deep learning. Plus his super-popular online course Learning How To Learn with Barbara Oakley.

 BI 014 Konrad Kording: Regulators, Mount Up! | File Type: audio/mpeg | Duration: 00:41:34

Konrad and I discuss his work automatically detecting potential image fraud in scientific papers, his take on consciousness, and plenty more.

 BI 013 Dileep George: Vicarious Robot AI | File Type: audio/mpeg | Duration: 00:52:27

Dileep and I talk about how his company, Vicarious, aims to create general artificial intelligence for robots, using tons of inspiration from brain structure and function. We also discuss his recent graphical model that, among other things, breaks CAPTCHAs with very few training examples.

 BI 012 Niko Kriegeskorte: Black Box, White Box | File Type: audio/mpeg | Duration: 01:06:25

Niko and I discuss cognitive computational neuroscience as an emerging fusion between cognitive science, computational neuroscience, and artificial intelligence - and how it all fits together. Plus we talk about the conference by that name.

 BI 011 Grace Lindsay: Visual Attention in CNNs | File Type: audio/mpeg | Duration: 00:50:30

Grace shares her recent work adding an attention signal to convolutional neural networks - ones that emulate the ventral visual stream in the brain - to test the "feature gain similarity" model of attention. Lots more, of course. Click the show to access the show notes.

 BI 010 Adam Marblestone: Brain Cost Functions | File Type: audio/mpeg | Duration: 01:04:46

Adam and I discuss the possibility there are cost functions optimized in the brain, where and how it might work, Marvin Minsky's Society of Mind, and lots more.

 BI 009 Blake Richards: Deep Learning in the Brain | File Type: audio/mpeg | Duration: 01:11:00

Blake and I discuss his recent work exploring one way credit assignment could occur in the brain, using different regions within a single cortical neuron to encode the necessary signal.

 BI 008 Joshua Glaser: Supervised ML for Neuroscience | File Type: audio/mpeg | Duration: 00:53:34

Josh and I talk about all the ways supervised machine learning can be used in neuroscience research, and we walk through how a variety of machine learning algorithms perform decoding on a few neural data sets.

 BI 007 Daniel Yamins: Infant AI and CNNs | File Type: audio/mpeg | Duration: 01:01:48

In this episode, Dan Yamins and I talk about how he uses hierarchical convolutional neural networks to model the ventral visual stream, finding that the units in his model correspond to neurons in progressive layers of the brain. We also delve into the AI agents he develops that learn how to play through intrinsic motivation. Click the episode to get the show notes.

 BI 006 Ryan Poplin: Deep Solutions | File Type: audio/mpeg | Duration: 00:37:16

Ryan and I go deep (pun intended) on convolutional neural networks and how he uses them to solve problems in medical risk factor discovery and improve genome sequencing, and more. Click the episode for the show notes

 BI 005 David Sussillo: RNNs are Back! | File Type: audio/mpeg | Duration: 00:45:39

David and I cover recurrent neural networks (RNNs), his work using RNNs to study motor brain processes, how dynamical systems theory is a useful approach to brains and AI, and more. Click the episode for the show notes.

 BI 004 Mark Humphries: Learning to Remember | File Type: audio/mpeg | Duration: 00:41:39

What does it mean to be a neural data scientist? Mark and I talk about that, his work discovering how rat prefrontal cortex learns to remember, and a bunch of AI topics he's written about via his Medium blog. Click the episode for the show notes

 BI 003 Blake Porter: Effortful Rats | File Type: audio/mpeg | Duration: 00:42:47

Blake and I talk about his work studying effort and decision making in the hippocampus of rats, how AI bots are taking over the gaming world, and more. Click the episode for the show notes

 BI 002 Steven Potter Part 2: Brains in Dishes | File Type: audio/mpeg | Duration: 01:11:23

We talk about how he got the embodied cultured networks to actually work, the hurdles they had to jump through, the rise of citizen science, the Maker movement, and more. Click the episode for the show notes

Comments

Login or signup comment.