Interpretability vs Neuroscience [rough note]

A list of advantages that make understanding artificial nerural networks much easier than biological ones.

Interpretability vs Neuroscience [rough note] -- colah's blog Interpretability vs Neuroscience Six major advantages which make artificial neural networks much easier to study than biological ones. Posted on March 12th, 2021 This article is a rough note. Writing rough notes allows me share more content, since polishing takes lots of time. While I hope it's useful, it's likely lower quality and less carefully considered than my usual articles. It's very possible I wouldn't stand by this content if I thought about it more. I study what goes on inside artificial neural networks. I don’t know anyth

related reading

• Analogies between Biology and Deep Learning [rough note] -- colah's blogcolah.github.io
• Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
• Home - colah's blogcolah.github.io
• Neural networks are not already cleanlesswrong.com
• A Recipe for Training Neural Networkskarpathy.github.io
• Neuroscience is pre-paradigmatic. Consciousness is whytheintrinsicperspective.com
• Could a Neuroscientist Understand a Microprocessor? | PLOS Computational Biologyjournals.plos.org
• Neural Networks, Types, and Functional Programming -- colah's blogcolah.github.io
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Mechanistic Interpretability: A Challenge Common to Both Artificial and Biological Intelligencekempnerinstitute.harvard.edu
• A Recipe for Training Neural Networkskarpathy.github.io
• Feature Visualizationdistill.pub