horrible-dong/DPA
[NeurIPS 2024] Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
This project offers a new way to improve how Artificial Neural Networks (ANNs) process information. It takes an existing ANN and enhances its ability to focus on important data signals while ignoring irrelevant 'noise'. The output is a more efficient and accurate ANN, useful for machine learning engineers and researchers building robust AI models.
Use this if you are a machine learning engineer or researcher looking to improve the accuracy and efficiency of your neural network models by reducing internal signal noise without adding new parameters.
Not ideal if you are looking for an off-the-shelf solution for a specific data science task rather than a tool to optimize the underlying neural network architecture itself.
Stars
8
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/horrible-dong/DPA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)