A set of LangChain Tutorials from my youtube channel

Characterizing possible failure modes in physics-informed neural networks.

Code for the paper "Understanding Generalization through Visualizations"

Exploring the Geometry and Topology of Neural Network Loss Landscapes

Python energy landscape explorer

CUDA-accelerated PyTorch implementation of t-SNE

Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning adjustable weight coefficients.

A library for scientific machine learning and physics-informed learning

Universal Representations: A Unified Look at Multiple Task and Domain Learning

The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

A PyTorch Library for Multi-Task Learning

2024 up-to-date list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.

Create animations for the optimization trajectory of neural nets

This in my Demo of Chen et al. "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks" ICML 2018

recurrent neural network based project

Animation of the motion a double-pendulum. Both Julia and Python versions of the code are given.

Counting the number of conservation laws from trajectory data

Code for our paper "Hamiltonian Neural Networks"

Software for producing disconnectivity and metric disconnectivity graphs, and for calculating the principal components of chemical systems.

Pytorch implementation of convolutional neural network visualization techniques

Code for visualizing the loss landscape of neural nets

Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch