Gradient Checking: Demonstrates 1D and ND gradient checking techniques to verify the accuracy of gradients in neural networks. Inspired by DeepLearning.AI's Deep Learning Specialization.

Desenvolvimento de ferramenta para efetuar a Modelagem e a Migração Sísmica de um modelo 2D.

Implementing Neural network from scratch

I build the Micrograd autogradient engine, which is a functioning neural network with forward pass, backward propagation, and stochastic gradient descent, all built from scratch. This is derived from the great @karpathy micrograd lecture. Each notebook is complete with Andrei's lecture code and speech, as well as my own code, anecdotes and addition

Tugas praktikum Data Mining I

A gentle introduction to custom gradient propagation for ML application in which parameters of LTI systems have to be optimized. This example enables the integration of control theory with machine learning, for the development of Physical-Informed Neural Networks (PINNs)

This repository contains the solutions of Coursera course Intro to Deep Learning Solutions

This code uses computational graph and neural network to solve the five-layer traffic demand estimation in Sioux Falls network. It also includes comparison of models and 10 cross-validations.

Implementation of Artificial Neural Network from Scratch using Python and Jupyter Notebook

Tubes IF3270: Machine Learning in Forward and Backward Propagation Implementation

A.K.A. NUS ME5411 Final Project. Implemented a CNN framework without off-the-shelf libraries and its application for character recognition.

This notebook demonstrates a neural network implementation using NumPy, without TensorFlow or PyTorch. Trained on the MNIST dataset, it features an architecture with input layer (784 neurons), two hidden layers (132 and 40 neurons), and an output layer (10 neurons) with sigmoid activation.

搭建、深度学习、前向传播、反向传播、梯度下降和模型参数更新、classification、forward-propagation、backward-propagation、gradient descent、python、text classification

A C++ machine learning framework/library.

Deep Learning & Labs Course, NYCU, 2023

Neural Network using NumPy, V1: Built from scratch. V2: Optimised with hyperparameter search.

Digit Recognition Neural Network: Built from scratch using only NumPy. Optimised version includes HOG feature extraction. Third version utilises prebuilt ML libraries.

Fit functions using the Backpropagation Algorithm. 一个使用反向传播算法拟合函数的工具。

A feedforward neural network from scratch without any high level deep learning libraries. Pure mathematics and NumPy.