Search AI News
Find articles from 100+ AI sources
Found 188 results for "neural network"
Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel
Back to Articles Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel Published May 2,…
~Don't~ Repeat Yourself
Back to Articles Don't Repeat Yourself* Published April 5, 2022 Update on GitHub Upvote 55 +49 Patrick von…
Utility vs Understanding: the State of Machine Learning Entering 2022
The empirical utility of some fields of machine learning has rapidly outpaced our understanding of the…
Accelerating PyTorch distributed fine-tuning with Intel technologies
Back to Articles Accelerating PyTorch distributed fine-tuning with Intel technologies Published November 19,…
Scaling up BERT-like model Inference on modern CPU - Part 2
Back to Articles Scaling up BERT-like model Inference on modern CPU - Part 2 Published November 4, 2021…
Introducing Optimum: The Optimization Toolkit for Transformers at Scale
Back to Articles Introducing 🤗 Optimum: The Optimization Toolkit for Transformers at Scale Published…
Scaling-up BERT Inference on CPU (Part 1)
Back to Articles Scaling up BERT-like model Inference on modern CPU - Part 1 Published April 20, 2021 Update…
DALL·E: Creating images from text
We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of…
CLIP: Connecting text and images
We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural…
Block Sparse Matrices for Smaller and Faster Language Models
Back to Articles Block Sparse Matrices for Smaller and Faster Language Models Published September 10, 2020…
AI and efficiency
We’re releasing an analysis showing that since 2012 the amount of compute needed to train a neural net to…
OpenAI Microscope
We’re introducing OpenAI Microscope, a collection of visualizations of every significant layer and neuron…
Solving Rubik’s Cube with a robot hand
We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The…
Testing robustness against unforeseen adversaries
We’ve developed a method to assess whether a neural network classifier can reliably defend against…
Generative modeling with sparse transformers
We’ve developed the Sparse Transformer, a deep neural network which sets new records at predicting what…
How AI training scales
We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability…
OpenAI Five
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
Discovering types for entity disambiguation
We’ve built a system for automatically figuring out which object is meant by a word by having a neural…
Block-sparse GPU kernels
We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures:…
Robust adversarial inputs
We’ve created images that reliably fool neural network classifiers when viewed from varied scales and…