EMI-Group
Pinned Loading
Repositories
- evogp Public
A GPU-accelerated library for Tree-based Genetic Programming, leveraging PyTorch and custom CUDA kernels for high-performance evolutionary computation. It supports symbolic regression, classification, and policy optimization with advanced features like multi-output trees and benchmark tools.
EMI-Group/evogp’s past year of commit activity - snn-temporal-fusion Public
Efficient method for accelerating spiking neuron computation on GPU, enabling faster SNN training. Includes demos and a self-buildable CUDA kernel tutorial.
EMI-Group/snn-temporal-fusion’s past year of commit activity - spikefpn Public
A spiking feature pyramid network with adaptive neurons for event-based vision tasks in autonomous driving, evaluated on GAD and N-CARS datasets.
EMI-Group/spikefpn’s past year of commit activity - evorl Public
EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided Reinforcement Learning (ERL), AutoRL, and seamless integration with GPU-optimized simulation environments.
EMI-Group/evorl’s past year of commit activity - metade Public
MetaDE is a GPU-accelerated evolutionary framework that optimizes Differential Evolution (DE) strategies via meta-level evolution. Supporting both JAX and PyTorch, it dynamically adapts mutation and crossover strategies for efficient large-scale black-box optimization.
EMI-Group/metade’s past year of commit activity - evoxbench Public
Transforming Neural Architecture Search (NAS) into multi-objective optimization problems. A benchmark suite for testing evolutionary algorithms in deep learning.
EMI-Group/evoxbench’s past year of commit activity
Most used topics
Loading…