Infrastructure page 67

OpenAI News July 01, 2017 07:00

Teacher–student curriculum learning

We propose Teacher–Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on. We describe a...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News April 10, 2017 07:00

Stochastic Neural Networks for hierarchical reinforcement learning

Deep reinforcement learning has achieved many impressive results in recent years. However, tasks with sparse rewards or long horizons continue to pose significant challenges. To tackle these important problems, we propose a general framework that first...

Topics: Policy Infrastructure

Entities: Policy Infrastructure

OpenAI News February 08, 2017 08:00

Adversarial attacks on neural network policies

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we...

Topics: Policy Infrastructure

Entities: Policy Infrastructure

OpenAI News January 19, 2017 08:00

PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications

PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at this https URL⁠(opens in a new window). Our implementation contains a number of...

Topics: Models Infrastructure

Entities: Models Infrastructure

OpenAI News December 05, 2016 08:00

Universe

We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s supply of games, websites and other applications.

Topics: Infrastructure

Entities: Infrastructure

OpenAI News November 11, 2016 08:00

A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models

Generative adversarial networks (GANs) are a recently proposed class of generative models in which a generator is trained to optimize a cost function that is being simultaneously learned by a discriminator. While the idea of learning cost functions is...

Topics: Models Infrastructure

Entities: Models Infrastructure

OpenAI News November 02, 2016 07:00

Extensions and limitations of the neural GPU

The Neural GPU is a recent model that can learn algorithms such as multi-digit binary addition and binary multiplication in a way that generalizes to inputs of arbitrary length. We show that there are two simple ways of improving the performance of the...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News October 18, 2016 07:00

Semi-supervised knowledge transfer for deep learning from private training data

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the model may therefore...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News October 11, 2016 07:00

Transfer from simulation to real world through learning deep inverse dynamics model

Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and optimization, and even more so to policies obtained from reinforcement...

Topics: Models Policy Infrastructure

Entities: Models Policy Infrastructure

OpenAI News August 29, 2016 07:00

Infrastructure for deep learning

Deep learning is an empirical science, and the quality of a group’s infrastructure is a multiplier on progress. Fortunately, today’s open-source ecosystem makes it possible for anyone to build great deep learning infrastructure.

Topics: Infrastructure

Entities: Infrastructure

OpenAI News May 25, 2016 07:00

Adversarial training methods for semi-supervised text classification

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations...

Topics: Infrastructure

Entities: Infrastructure

OpenAI News February 25, 2016 08:00

Weight normalization: A simple reparameterization to accelerate training of deep neural networks

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning of the...

Topics: Models Infrastructure

Entities: Models Infrastructure