liuyao12/ConvNets-PDE-perspective
an Open Collaborative project to explore the implications — theoretical or practical — of the PDE perspective of ConvNets
This project explores how Convolutional Neural Networks (ConvNets), often used for image recognition and analysis, can be understood and designed using concepts from Partial Differential Equations (PDEs). It views ConvNet operations like 3x3 convolutions and skip connections as numerical methods for solving PDEs. Researchers and advanced students in machine learning and applied mathematics can use this perspective to develop new ConvNet architectures.
No commits in the last 6 months.
Use this if you are a researcher or advanced student interested in the theoretical underpinnings of ConvNets and want to explore novel architectural designs inspired by mathematical concepts of PDEs.
Not ideal if you are looking for a plug-and-play library to immediately train or deploy existing ConvNet models for practical applications.
Stars
21
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/liuyao12/ConvNets-PDE-perspective"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.