Identifying Generalization Properties in Neural Networks
While it has not yet been proven, empirical evidence suggests that model generalization is related to local properties of the optima which can be described via the Hessian. We connect model generalization with the local property of a solution under the PAC-Bayes paradigm. In particular, we prove that model ge ...
The Natural Language Decathlon
Deep learning has significantly improved state-of-the-art performance for natural language processing tasks like machine translation, summarization, question answering, and text classification. Each of these tasks is typically studied with a specific metric, and performance is often measured on a set of stand ...
A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
In the same way that human decisions can be influenced by cognitive biases, decisions made by artificially intelligent systems can be vulnerable to algorithmic biases. Because AI systems depend heavily on the data used to train them, any bias in the data can then bias the decisions that system makes. In order ...
We annually publish and present our findings at top NLP and computer vision conferences.See all publications
We distill our state-of-the-art research papers down to their simplest components. So whether you’re a busy executive or an aspiring AI researcher, you’ll find our blog posts articulate, efficent, and easy to understand.Read our blog
Collaborate on breakthrough open source artificial intelligence technology.Collaborate
Connecting deep learning researchers with the world's smartest CRM.Apply