evojax
Neuroevolution accelerator
A toolkit for accelerating neuroevolution with neural networks on accelerators
856 stars
23 watching
88 forks
Language: Jupyter Notebook
last commit: 6 months ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
google/objax | An open-source machine learning framework designed to simplify and accelerate research | 772 |
giuse/dne | A set of neuroevolution experiments with deep networks using unsupervised learning and evolutionary reinforcement learning algorithms | 125 |
nngen/nngen | Generates hardware-specific accelerator designs for neural networks | 340 |
neurotechx/eeg-expy | A collection of classic EEG experiments implemented in Python to democratize cognitive neuroscience research using affordable and scalable hardware | 453 |
jiasenlu/vilbert_beta | A pre-trained model and toolset for performing vision-and-language tasks using a specific neural network architecture. | 473 |
nnaisense/evotorch | An evolutionary computation library built on top of PyTorch for solving optimization problems in various fields. | 1,026 |
bergel/neat | An implementation of the Neuroevolution through Augmenting Topologies (NEAT) algorithm for evolutionary optimization of neural networks in Pharo. | 16 |
adaptive-intelligent-robotics/qdax | Accelerates Quality-Diversity algorithms to run on hardware accelerators and massive parallelization in minutes. | 270 |
roberttlange/evosax | An evolution strategy optimization library built on top of JAX and XLA for high-throughput acceleration | 514 |
apache/tvm-vta | A comprehensive hardware design stack for accelerating deep learning models | 258 |
ibm/aihwkit | An open source toolkit for developing and training neural networks on analog computing devices | 365 |
zueve/neurolab | A Python library for building and training neural networks. | 163 |
catalystneuro/ndx-simulation-output | An extension for large-scale simulation data in neurophysiology research | 4 |
aria42/flare | A Clojure library for building and manipulating dynamic neural net graphs with pluggable tensor operations and hardware acceleration. | 285 |
zampino/exnn | An Elixir framework for building and training evolutive neural networks. | 100 |