Over the past five years, deep learning (DL) frameworks such as TensorFlow and PyTorch have been introduced to enable developers to quickly prototype new machine learning models. Most such frameworks however still struggle with the implementation of sequential decision methods, especially with regard to reinforcement learning (RL) algorithms.

To fill…

While it is generally accepted that network depth is responsible for the high performance of today’s deep learning (DL) models, adding depth also brings downsides such as increased latency and computational burdens, which can bottleneck progress in DL. Is it possible to achieve similarly high performance without deep networks?

In…

Generating AI agents that can collaborate effectively with humans is a long-standing challenge in the broad field of human-machine interaction. Recent studies have shown that it is possible for agents to reach human-level performance using model-free reinforcement learning (RL) without human data via self-play, where an agent learns from repeated…

In the new paper Learning in High Dimension Always Amounts to Extrapolation, a team from Facebook AI Research and New York University that includes Yann LeCun theoretically and empirically challenges the machine learning (ML) community’s conventional wisdom regarding interpolation, demonstrating that it almost never happens on high-dimensional (>100) datasets.

Interpolation…

Photo-realistic free-view image synthesis of real-world scenes is an intriguing and important task in the computer vision field. Although the development of generative adversarial networks (GANs) has advanced such image synthesis to stunning new levels of quality, GANs cannot synthesize high-resolution 3D images and tend to be computationally expensive.

In…

Machine learning researchers have in recent years turned their attention to neural language models to solve natural language understanding (NLU) tasks that require extensive world knowledge. To obtain sufficient factual knowledge, such advanced models require the retrieving and assimilating of factual information from multiple text sources.

In a new study…

Deep generative models that apply a likelihood function to data distribution have made impressive progress in modelling different sources of data such as images, text and video. A popular such model type is autoregressive models (ARMs), which, although effective, require a pre-specified order for their data generation. …

Studies have shown that scaling up powerful pretrained models and their training data sizes significantly improves performance, and that these performance improvements can transfer to downstream tasks, even in few-shot settings. But is there a limit to the performance improvements attainable via such model size and training data scale-ups?

To…