Image morphing without reference points by applying warp maps and optimizing over them.

Implementing Multiple Layer Neural Network from Scratch

A PyTorch implementation of Learning to learn by gradient descent by gradient descent

深度学习常用优化方法详解

Code and data for Neural Holography

numerical optimization in pytorch

Some experiments about Machine Learning

Code for https://fosterelli.co/executing-gradient-descent-on-the-earth

"Learning to learn by gradient descent by gradient descent "by PyTorch -- a simple re-implementation.

Variational Inference in Gaussian Mixture Model

An Image classifier to identify whether the given image is Batman or Superman using a CNN with high accuracy. (From getting images from google to saving our trained model for reuse.)

sopt:A simple python optimization library

CIFAR 10 image dataset

Statistical optimization for AI and machine learning

Toy implementations of some popular ML optimizers using Python/JAX

Amortized version of the differentially private SGD algorithm published in "Deep Learning with Differential Privacy" by Abadi et al. Enforces privacy by clipping and sanitising the gradients with Gaussian noise during training.

Meta_SCMT is a software to inverse design large-area dielectric metasurface. The key factor that differentiates the Meta_SCMT from current Local Periodic Approximation(LPA) based methods is that Meta_SCMT can achieve fullwave-level accuracy with much less computational resource.

This project shows the area division process in Multi-Agent exploration using Cyclic Gradient Descent and also how Cooperative Perceptional Messages are used in V2V communication to share information among agents in about the environment.

This repository is updated by a number of introductory projects to deep learning with Python.

AdaX: Adaptive Gradient Descent with Exponential Long Term Momery