Mentioned in the show:

Dan’s Stanford Neuroscience and Artificial Intelligence Laboratory:

The 2 papers we discuss

Performance-optimized hierarchical models predict neural responses in higher visual cortex

Learning to Play with Intrinsically-Motivated Self-Aware Agents

ImageNet as one of the most important things to stimulate research in AI, developed by these folks.

Ventral visual stream (as opposed to the Dorsal stream).

Retinotopy

Convolutional neural networks were inspired by Kunihiko Fukushima’s Neocognitron

2 modern of approaches to solve the ImageNet database:

Google’s NASNet architecture, with about 12 layers

Microsoft’s super deep ResNet.

Object permanence and some video examples

The distinction between the intrinsic motivation of Dan and colleagues’ AI agent and the reinforcement learning motivation of the OpenAI 5 team

[bctt tweet=”Check out episode 6 of the Brain Inspired podcast: Deep learning, eyeballs, and brains” username=”pgmid”]

Check out episode 6 of the Brain Inspired podcast: Deep learning, eyeballs, and brainsClick To Tweet

Mentioned in the show

Ryan Poplin

What is a convolutional neural network?

Here’s a good summary. Here’s another good summary.

Deep learning on eye images: CV risk factors can be predicted from retinal fundus images

DeepVariant: Deep learning on genomics

The paper: Creating a universal SNP and small indel variant caller with deep neural networks

A nice, less technical summary of the work

The code on Github

 

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.

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