A deep learning library for use in high-performance computing applications in modern Fortran

A simple Feedforward Neural Network library for Rust

C++ Feedforward Neural Network w/ WASM Inferencing & Vue3 UI for MNIST Digit Classification

Machine learning predicting potential fires in Brazil.

A feed-forward neural network for digital classification

Implementation of a Fully Connected Neural Network, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) from Scratch, using NumPy.

This project implements various machine learning models, including Logistic Regression, Random Forest, and FNN, to predict heart disease. Utilizing Gradio for a user-friendly interface and MLflow for model management, it aims to enhance diagnostic accuracy.

SkimLit is a deep learning project aimed at simplifying the understanding of medical research literature. It automatically classifies sentences from medical abstracts into specific categories like **Introduction**, **Conclusion**, **Results**, etc.

Deep learning for Natural Language Processing

Digit MNIST optimization classification project, our goal is to minimize the loss function using several optimizers

A Feed-Forward Neural Network created with the C99 standard

Digit Recognition using Feed Forward Neural Network in Pytorch

Feed-forward neural network implementation in C with SIMD instructions

Android/iOS app for Diabetes monitoring and prediction. (UI-based features & Predictive Analysis using Deep Learning)

PyTorch detailed analysis to create Machine learning to Deep learning model

A web application hosted on Streamlit to predict customer churn using a deep learning model.

We present an hybrid PLC technique where a feed-forward neural network and an autoregressive model cooperate in order to reconstruct the lost samples.

A wrist-worn device and monitoring system implements user-file-memory management system for a person with Body-focused Repetitive Behavior

The handbook is structured to facilitate a clear understanding of deep learning principles, starting with basic neural network architecture and gradually advancing to complex topics such as convolutional neural networks (CNNs)