Brainstorm - Fast, flexible and fun neural networks.
A discontinued Python neural network framework designed for fast, flexible experimentation with CPU and GPU backends.
What is Brainstorm - Fast, flexible and fun neural networks.?
Brainstorm was a Python-based neural network framework designed for fast, flexible experimentation with neural networks. It provided a unified API for both CPU and GPU computations through abstracted handlers, supporting various layer types including recurrent networks, convolutions, and normalization layers. The framework aimed to make neural network research more accessible and enjoyable through clean abstractions.
Researchers and developers working on neural network experiments who wanted a flexible Python framework with both CPU and GPU support. Particularly suited for those exploring different network architectures and needing hardware abstraction.
Brainstorm offered a unique handler-based architecture that abstracted computational backends, allowing the same code to run on both CPU and GPU without modification. Its Python-native design and focus on experimentation made it appealing for research prototyping before larger frameworks dominated the space.
Overview
Fast, flexible and fun neural networks.
Use Cases
Best For
- Prototyping neural network architectures in Python
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
