Stars
TinyTNAS is a hardware-aware, multi-objective, time-bound Neural Architecture Search (NAS) tool designed for TinyML time series classification. Unlike GPU-based NAS methods, it runs efficiently on …
Zero-Shot NAS for General Time-Series Analysis with Time-Frequency Aware Scoring
This repository showcases three innovative projects combining advanced machine learning (LSTM, Random Forest) with meta-heuristic algorithms (Firefly, Artificial Bee Colony). These hybrid approache…
Electricity price (energy demand) forecasting using different ML, DL, stacked DL and hybrid methods (XGBoost, GRU, LSTM, CNN, CNN-LSTM, LSTM-Attention, Hybrid GRU-XGBoost and Hybrid LSTM-Attention-…
LSTM based on MAML framework for runoff simulation
This is a collection of our zero-cost NAS and efficient vision applications.
Basic implementation of [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578).
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
《Machine Learning: A Probabilistic Perspective》（Kevin P. Murphy）中文翻译和书中算法的Python实现。