Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
Updated
May 8, 2024 - Python
Artificial neural networks (ANN) are computational systems that "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
An Open Source Machine Learning Framework for Everyone
A personal research and development (R&D) lab that facilitates the sharing of knowledge.
Livermore Big Artificial Neural Network Toolkit
PennyLane is a cross-platform Python library for differentiable programming of quantum computers. Train a quantum computer the same way as a neural network.
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
On-device AI across mobile, embedded and edge for PyTorch
Common machine learning algorithm implementations
A Machine Learning framework from scratch in Pure Mojo 🔥
Supercharge Your Model Training
This will utilize neural network and machine learning models to paper trade on the stock market.
Neural Network for tic-tac-toe game.
Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
A lightweight library for PyTorch training tools and utilities
Estimates airborne drone global position by matching video to map retrieved from onboard GIS server.
Segmentation using Deep Learning
High-efficiency floating-point neural network inference operators for mobile, server, and Web
Uma rede neural recorrente treinada com processamento de linguagem natural, para a classificação de sentimentos. 💬
Comparative analysis of computational modeling of acoustic wave propagation using neural network-based methods.
Jacobian-Enhanced Neural Networks (JENN) are fully connected multi-layer perceptrons, whose training process was modified to account for gradient information. Specifically, the parameters are learned by minimizing the Least Squares Estimator (LSE), modified to minimize prediction error of both response values and partial derivatives.