Transformer-based neural networks have revolutionized natural language processing and computer vision fields due to their undeniably powerful performance, but most of the state-of-the-art models reach ...

This Python package implements the activation function transformations, weight initializations, and dataset preprocessing used in Deep Kernel Shaping (DKS) and Tailored Activation Transformations (TAT ...

Hello, in #29587 we had a good discussion about adding JAX transformations for 1) scan-like functionality and 2) batched vmapping (perhaps jax.bmap?). The discussion has my pitch for why I think this ...

Abstract: The radar ambiguity function is useful as a criterion of goodness for modulation signals used to discriminate the range and range-rate of point targets. It is often desirable to change ...