Implementation of a Physics Informed Neural Network (PINN) written in Tensorflow v2, which is capable of solving Partial Differential Equations.

Repository with material used in the Adaptive Signal Processing course (PPgEE-UFCG).

In this project, I implement an enhanced active contour method that uses discrete wavelet transform for energy minimization to increase the accuracy.

Official implementation of "Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes"

A curated repository of papers on the Hessian of deep neural networks.

This repository contains wrapper scripts for running transition state and IRC (Intrinsic Reaction Coordinate) calculations using Sella and IRC ASE optimizers for the Sella package.

Dual number classes for automatic differentiation including for higher order derivatives

This is my project about liver vessel segmentation in CT images based on hessian matrix and U-Net networks

This project investigates the relationship between neural network optimization techniques and the Hessian matrix in two-layer neural networks. The study focuses on understanding how different network architectures and optimization strategies impact the Hessian matrix and overall model performance.

A JAX + SymPy based project that explores optimization in ML using hessian matrix and graidents.

The implementation of advanced mathematical optimization methods

Code related to the paper: Hartoyo, A., Argasiński, J., Trenk, A., Przybylska, K., Błasiak, A., & Crimi, A. (2025). Synergistic eigenanalysis of covariance and Hessian matrices for enhanced binary classification on health datasets. Computers in Biology and Medicine, 190, 109985.

Projeto desenvolvido como parte de um laboratorio interativo de alta performance, abordando a anatomia matematica da IA. Implementado com .NET 10 e C# 13, incluindo conceitos de Algebra Linear, Calculo Multivariavel e Teoria da Probabilidade com foco em Redes Neurais e Otimizacao.

PyTorch tools for Hessian-related operations

Learning Network using Hessian Optimization in PyTorch