Get the latest tech news

Ilya Sutskever: learn these 30 papers to know 90% of what matters [in ML] today

A Folder from Cosmic The Annotated Transformer ↗ The First Law of Complexodynamics ↗ The Unreasonable Effectiveness of RNNs ↗ Understanding LSTM Networks ↗ Recurrent Neural Network Regularization ↗ Keeping Neural Networks Simple by Minimizing the Description Length of the Weights ↗ Pointer Networks ↗ ImageNet Classification with Deep CNNs ↗ Order Matters: Sequence to sequence for sets ↗ GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism ↗ Deep Residual Learning for Image Recognition ↗ Multi-Scale Context Aggregation by Dilated Convolutions ↗ Neural Quantum Chemistry ↗ Attention Is All You Need ↗ Neural Machine Translation by Jointly Learning to Align and Translate ↗ Identity Mappings in Deep Residual Networks ↗ A Simple NN Module for Relational Reasoning ↗ Variational Lossy Autoencoder ↗ Relational RNNs ↗ Quantifying the Rise and Fall of Complexity in Closed Systems: The Coffee Automaton ↗ Neural Turing Machines ↗ Deep Speech 2: End-to-End Speech Recognition in English and Mandarin ↗ Scaling Laws for Neural LMs ↗ A Tutorial Introduction to the Minimum Description Length Principle ↗ Machine Super Intelligence Dissertation ↗ PAGE 434 onwards: Komogrov Complexity ↗ CS231n Convolutional Neural Networks for Visual Recognition ↗.

Keeping Neural Networks Simple by Minimizing the Description Length of the Weights GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism Quantifying the Rise and Fall of Complexity in Closed Systems: The Coffee Automaton

Get the Android app