haiku

We have hosted the application haiku in order to run this application in our online workstations with Wine or directly.

Quick description about haiku:

Haiku is a library built on top of JAX designed to provide simple, composable abstractions for machine learning research. Haiku is a simple neural network library for JAX that enables users to use familiar object-oriented programming models while allowing full access to JAX�s pure function transformations. Haiku is designed to make the common things we do such as managing model parameters and other model state simpler and similar in spirit to the Sonnet library that has been widely used across DeepMind. It preserves Sonnet�s module-based programming model for state management while retaining access to JAX�s function transformations. Haiku can be expected to compose with other libraries and work well with the rest of JAX. Similar to Sonnet modules, Haiku modules are Python objects that hold references to their own parameters, other modules, and methods that apply functions on user inputs.

Features:

• JAX is a numerical computing library that combines NumPy
• Haiku provides two core tools: a module abstraction
• Haiku is a simple neural network library for JAX
• hk.Modules are Python objects that hold references to their own parameters
• Haiku has been tested by researchers at DeepMind at scale.
• Haiku is a library, not a framework

Programming Language: Python.
Categories: