Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these…
All-neural, end-to-end ASR systems gained rapid interest from the speech recognition community. Such systems convert speech input to text units…
Virtual assistants make use of automatic speech recognition (ASR) to help users answer entity-centric queries. However, spoken entity recognition is…
We introduce CVNets, a high-performance open-source library for training deep neural networks for visual recognition tasks, including classification, detection, and…
Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider…
Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel.…
The practical success of overparameterized neural networks has motivated the recent scientific study of interpolating methods, which perfectly fit their…
Understanding the building blocks and design choices of graph neural networks.
What components are needed for building learning algorithms that leverage the structure and properties of graphs?