Index · Papers

Papers

Browse abstracts and use AI to summarize papers you don't have time to read.

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

Machine Learning

Generative Adversarial Networks

Goodfellow et al.

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G and a discriminative model D.

Deep Learning

Highly accurate protein structure prediction with AlphaFold

Jumper et al.

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. We present a computational method, AlphaFold, that predicts protein structures with atomic accuracy.

Computational Biology

ImageNet Classification with Deep Convolutional Networks

Krizhevsky, Sutskever, Hinton

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet contest. On the test data, we achieved top-1 and top-5 error rates substantially better than the previous state-of-the-art.

Computer Vision