Reading list
hidden
Read within each track in order. Tracks are independent, so interleave them freely.
Philosophy of Mind
Identity theory to functionalism, computationalism, qualia, and the hard problem.
- Computing Machinery and Intelligence - Alan Turing
- Sensations and Brain Processes
- The Nature of Mental States
- What Is It Like to Be a Bat?
- Minds, Brains, and Programs
- Could a Machine Think
- Epiphenomenal Qualia
- Troubles with Functionalism
- Quining Qualia
- Facing Up to the Problem of Consciousness
Early Modern Rationalism
Primary Descartes first, commentary second, Spinoza last.
- Meditations on First Philosophy - René Descartes
- Descartes - Bernard Williams
- Ethics - Benedict de Spinoza
Ancient Philosophy
Foundational Greek political philosophy, then Stoic practice.
Ilya Sutskever Deep Learning List
Start with the intuitive neural network pieces, then move through sequence models, convolutional nets, attention, memory, scaling, and compression.
- The Unreasonable Effectiveness of Recurrent Neural Networks
- Understanding LSTM Networks
- Recurrent Neural Network Regularization - Wojciech Zaremba
- Pointer Networks - Oriol Vinyals
- Order Matters Sequence to Sequence for Sets - Oriol Vinyals
- Neural Machine Translation by Jointly Learning to Align and Translate - Dzmitry Bahdanau
- ImageNet Classification with Deep Convolutional Neural Networks - Alex Krizhevsky
- Deep Residual Learning for Image Recognition - Kaiming He
- Identity Mappings in Deep Residual Networks - Kaiming He
- Multi-Scale Context Aggregation by Dilated Convolutions - Fisher Yu
- Neural Message Passing for Quantum Chemistry - Justin Gilmer
- A Simple Neural Network Module for Relational Reasoning - Adam Santoro
- Relational Recurrent Neural Networks - Adam Santoro
- Neural Turing Machines - Alex Graves
- Attention Is All You Need - Ashish Vaswani
- The Annotated Transformer
- Deep Speech 2 End-to-End Speech Recognition in English and Mandarin - Dario Amodei
- GPipe Easy Scaling with Micro-Batch Pipeline Parallelism - Yanping Huang
- Scaling Laws for Neural Language Models - Jared Kaplan
- Variational Lossy Autoencoder - Xi Chen
- Keeping Neural Networks Simple by Minimizing the Description Length of the Weights - Geoffrey E Hinton
- A Tutorial Introduction to the Minimum Description Length Principle - Peter Grunwald
- Kolmogorov Complexity and Algorithmic Randomness - A Shen V A Uspensky N Vereshchagin
- The First Law of Complexodynamics
- Quantifying the Rise and Fall of Complexity in Closed Systems The Coffee Automaton - Scott Aaronson
- Machine Super Intelligence - Shane Legg