Podcast: Play in new window | Download (Duration: 22:46 — 15.1MB) | Embed
Subscribe: Apple Podcasts | Email | RSS | More
Bits and brains and bots
If we could look closely at every last cell in your brain, and learn enough to simulate them on a computer, would a detailed enough simulation of your brain think? Today, we talk about artificial neural networks—an AI method that is very loosely based on how biological brains work. A bit of history, a bit of confusion, and a bit about how our latest batch of digital organisms might use one.
Phil couldn’t stop laughing at the name. Here’s an episode I did before Phil joined the show on the Perceptron, one of the first machines built based on how the brain works.
Here’s a nice sight with some history on neural networks.
A ‘Brief’ History of Neural Nets and Deep Learning, Part 1
Here’s a page on how graphics cards can be used to run neural networks much faster.
Why are GPUs necessary for training Deep Learning models?
And here’s something cute MythBusters did on the difference between a CPU and a GPU.