卒業研究の実験のために書いたソースコードを改修したものです。全てのコードを1から書きました。(自動生成されたコードであるcython_wl_kernel.cppを除く)
-
Updated
Oct 13, 2022 - Python
卒業研究の実験のために書いたソースコードを改修したものです。全てのコードを1から書きました。(自動生成されたコードであるcython_wl_kernel.cppを除く)
[TCAD'23] TransCODE: Co-design of Transformers and Accelerators for Efficient Training and Inference
Neural architecture search framework based on reinforcement learning:"A Novel Approach to Detecting Muscle Fatigue Based on sEMG by Using Neural Architecture Search Framework"
Q. Yao, J. Xu, W. Tu, Z. Zhu. Efficient Neural Architecture Search via Proximal Iterations. AAAI 2020.
Official implementation for [Best Paper Award @ SoICT 2022] "Training-Free Multi-Objective and Many-Objective Evolutionary Neural Architecture Search with Synaptic Flow"
A proof of concept implementation of a Data Aware Neural Architecture Search.
Research on AutoML and Explainability.
BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks, ECCV 2022
This repository explores how far can you model biological vision solely with architecture and local learning?
[JAIR'23] FlexiBERT tool for Transformer design space exploration.
Official PyTorch Implementation of EGANS(TEC'23)
Differentiable neural architecture search
Neural architecture search with network morphism used for skin lesion analysis
Fast and Practical Neural Architecture Search (ICCV2019)
Réimplémentation des expériences de l'article Evo-NAS
卒業研究の実験のために書いたソースコードです。全てのコードを1から書きました。(自動生成されたコードであるcython_wl_kernel.cppを除く)
POPNASv3 development repository, a neural architecture search method developed for a master thesis by Andrea Falanti (Politecnico di Milano, academic year 2020-2021) and subsequently refined as research assistant for the AI-SPRINT european project.
Code implementing various Curriculum Learning training strategies in order to accelerate the training convergence of CNNs used for Image Recognition tasks.
Code for the CEC 2023 paper: Federated Bayesian Optimization for Privacy-preserving Neural Architecture Search
OSNASLib is a general one-shot NAS framework empowering uses to incorporate one-shot NAS methods into various tasks (e.g. face recongition) easily.
Add a description, image, and links to the neural-architecture-search topic page so that developers can more easily learn about it.
To associate your repository with the neural-architecture-search topic, visit your repo's landing page and select "manage topics."