1 repository
Awesome GitHub RepositoriesCombinator-Based Model Composition
The assembly of neural network architectures using high-level serial and branch combinators.
Distinct from Model Composition Architectures: Existing candidates focus on grammar parsing or general software design, not neural network structural combinators
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Combinator-Based Model Composition. Refine with filters or upvote what's useful.
Awesome Combinator-Based Model Composition GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- google/trax
google/trax
8,304Vezi pe GitHubTrax is a deep learning framework and hardware-agnostic tensor engine designed for designing and training neural networks. It serves as a research tool providing high-level combinators for composing complex architectures, alongside a dedicated library for building transformer models and a toolkit for reinforcement learning. The framework is distinguished by its support for reversible and sparse transformer architectures, which reduce memory and computational overhead. It enables a single set of model instructions to execute across different hardware backends without changing the underlying co
Uses high-level combinators to build modular deep learning architectures through serial and branch logic.
Python
