Code used to obtain the results for my master thesis in computer sciences at ULB.
-
Updated
Jun 5, 2023 - Jupyter Notebook
Code used to obtain the results for my master thesis in computer sciences at ULB.
Neural architecture search for deep learning models using neuroevolution with Cultural Algorithms (preview)
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)
Neural architecture search framework based on reinforcement learning:"A Novel Approach to Detecting Muscle Fatigue Based on sEMG by Using Neural Architecture Search Framework"
[TCAD'23] TransCODE: Co-design of Transformers and Accelerators for Efficient Training and Inference
Q. Yao, J. Xu, W. Tu, Z. Zhu. Efficient Neural Architecture Search via Proximal Iterations. AAAI 2020.
Tests I am performing on a Python package for building residual multi - layer perceptrons and tandem [any model] -> ResMLPs models, useful for effective transfer learning. A pypi package should be coming soon.
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
[JAIR'23] FlexiBERT tool for Transformer design space exploration.
Generating neural networks for diverse networking classification tasks via hardware-aware neural architecture search, Transactions on Computers 2023
This repository explores how far can you model biological vision solely with architecture and local learning?
Official PyTorch Implementation of EGANS(TEC'23)
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.
Comparative of the performance of computer vision models designed by hand and models designed using Hardware-Aware Neural Architecture Search (HW-NAS)
Replication of Neural Predictor for Neural Architecture Search with Tensorflow
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."