Building Convolutional Neural Networks From Scratch using NumPy

Implementing Neural Networks for Computer Vision in autonomous vehicles and robotics for classification, pattern recognition, control. Using Python, numpy, tensorflow. From basics to complex project

Sentiment analysis for Twitter's tweet (in Indonesia language) was built with 3 models to get a comparison in determining which model gives the best results for predicting a tweet to have a positive or negative meaning.

Simple MATLAB toolbox for deep learning network: Version 1.0.3

QReLU and m-QReLU: Two novel quantum activation functions for Deep Learning in TensorFlow, Keras, and PyTorch

layers

A facial emotion/expression recognition model created using CNN with Keras & Tensorflow

Convolutional Neural Network with just Numpy and no other MLLibs

Super Resolution's the images by 3x using CNN

Library which can be used to build feed forward NN, Convolutional Nets, Linear Regression, and Logistic Regression Models.

Neural Network to predict which wearable is shown from the Fashion MNIST dataset using a single hidden layer

Corruption Robust Image Classification with a new Activation Function. Our proposed Activation Function is inspired by the Human Visual System and a classic signal processing fix for data corruption.

A classifier to differentiate between Cat and Non-Cat Images

A small walk-through to show why ReLU is non linear!

Evaluation of multiple graph neural network models—GCN, GAT, GraphSAGE, MPNN and DGI—for node classification on graph-structured data. Preprocessing includes feature normalization and adjacency-matrix regularization, and an ensemble of model predictions boosts performance. The best ensemble achieves 83.47% test accuracy.

Neural Network from scratch without any machine learning libraries

Building Convolution Neural Networks from Scratch

This project predicts used car prices using a feedforward neural network regression model implemented in PyTorch. Features include car age, mileage, and other attributes. The pipeline supports feature normalization, train/validation/test splitting, and visualization of training and validation loss curves.

The objective of this project is to identify the fraudulent transactions happening in E-Commerce industry using deep learning.

NNTicks is a desktop neural-network-based tick predictor built in Python. It’s designed for binary tick trading and supports real-time predictions, neural network training, backtesting, and live visualization — all within a sleek PyQt6 interface.

This project creates a machine learning model that predicts the success of investing in a business venture.

Graph-level model optimizer for PyTorch: Conv+BN(+ReLU) fusion, redundant layer removal, latency profiling, and visualization. Perfect for ML compiler exploration and performance-aware model optimization.

Using MNSIT as a training dataset, this model is trained to predict the handwritten digits.

Lightweight neural network library written in ANSI-C supporting prediction and backpropagation for Convolutional- and Fully Connected neural networks

Text Generation

Twitter Sentiment Extraction using Custom Roberta Transformer Model and using Pre-trained model weights for prediction

This repository contains the implementation of a Convolutional Neural Network (CNN) with RELU for detecting image splicing forgeries. Image splicing is a common manipulation technique where parts of different images are combined to create a forged image.

A deep learning project using Convolutional Neural Networks (CNNs) to classify CIFAR-10 images. The model leverages data augmentation, batch normalization, and ReLU activation to improve performance and generalization. Includes training and evaluation scripts for multi-class image classification.

rede neural totalmente conectada, utilizando mini-batch gradient descent e softmax para classificação no dataset MNIST

Traffic signal identification using Keras LeNet architecture. Identify 43 different classes of images with over 90% accuracy.