Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux
- deep-learning
- deep-neural-networks
- gradient-descent
- automatic-differentiation
47,133 repositories indexed
49–62 of 62 · Most stars
Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux
A platform independent tensor library with autograd for the JVM
NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions
👩💻 Matrix and other math, accelerated by WebGPU and WASM
Deep learning model for single-cell inference of multi-omic profiles from a single input modality.
Working with time-dependent networks in Julia
A Python toolkit for quantum neural networks.
Deciphering cell-cell communication from spatially resolved transcriptomic data at single-cell resolution with subgraph-based attentional graph neural network
PyTorch implementation of "TGSA: Protein-Protein Association-Based Twin Graph Neural Networks for Drug Response Prediction with Similarity Augmentation"
Workbench for practical machine learning in Ruby.
DetecDiv provides a comprehensive set of tools to analyze time microscopy images using deep learning methods. The software structure is such that data can be processed either at the command line or using a graphical user-interface. Detecdiv classification models include : image classification and regression, semantic segmentation, LSTM networks to analyze data and image timeseries.
Distributed Simulation of Transport Networks
Interpretable drug response prediction with graph neural networks over drugs, cell lines, and genes.
Simulating Lorenz attractor on Golem.network