Skip to search formSkip to main contentSkip to account menu

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.
View PDF on arXiv (opens in a new tab)

AutoAugment: Learning Augmentation Strategies From Data

This paper describes a simple procedure called AutoAugment to automatically search for improved data augmentation policies, which achieves state-of-the-art accuracy on CIFAR-10, CIFar-100, SVHN, and ImageNet (without additional data).
View on IEEE (opens in a new tab)

AutoAugment: Learning Augmentation Policies from Data

This paper describes a simple procedure called AutoAugment to automatically search for improved data augmentation policies, which achieves state-of-the-art accuracy on CIFAR-10, CIFar-100, SVHN, and ImageNet (without additional data).
View PDF on arXiv (opens in a new tab)

Concrete Problems in AI Safety

A list of five practical research problems related to accident risk, categorized according to whether the problem originates from having the wrong objective function, an objective function that is too expensive to evaluate frequently, or undesirable behavior during the learning process, are presented.
View PDF on arXiv (opens in a new tab)

Adversarial Patch

A method to create universal, robust, targeted adversarial image patches in the real world, which can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class.
View PDF on arXiv (opens in a new tab)

Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow

Overall, users find the TensorFlow Graph Visualizer useful for understanding, debugging, and sharing the structures of their models.
View on IEEE (opens in a new tab)

DEFENSIVE QUANTIZATION: WHEN EFFICIENCY MEETS ROBUSTNESS

A novel Defensive Quantization (DQ) method is proposed by controlling the Lipschitz constant of the network during quantization, such that the magnitude of the adversarial noise remains non-expansive during inference.

Reward learning from human preferences and demonstrations in Atari

This work trains a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games and achieves strictly superhuman performance on 2 games without using game rewards.

SARN : Relational Reasoning through Sequential Attention

This paper proposes an attention module augmented relational network called SARN (Sequential Attention Relational Network) that can carry out relational reasoning by extracting reference objects and…

Exploring the Limits of Out-of-Distribution Detection

It is demonstrated that large-scale pre-trained transformers can improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities and a new way of using just the names of outlier classes as a sole source of information without any accompanying images is explored.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)