Code from Coursera Advanced Machine Learning specialization - Intro to Deep Learning - week 2.

Recognizing handwritten digits of the MNIST dataset featuring a deep learning model, providing a comprehensive solution for training, testing, and evaluating digit recognition.

This repository provides a Docker Compose configuration for training, evaluating, and inferring on the MNIST Hogwild dataset with PyTorch. It simplifies the workflow by integrating three services: train, evaluate, and infer, enabling an efficient and reproducible machine learning environment.

This repository performs Computer-Vision tasks on multiple Image Datasets using CNN based Networks.

Feedforward backpropagation neural network classifier for MNIST digit datatset

This repository codebase develops a CNN for MNIST dataset digit classification using PyTorch, fully containerized with Docker for effortless setup and environment consistency. It supports training from scratch, resuming from checkpoints, and evaluation. The Docker setup ensures easy reproducibility across different machines.

Neural networks were utilized for diverse classification tasks, such as predicting breast cancer malignancy and classifying handwritten digits in the MNIST dataset. Both projects demonstrated the effectiveness of neural networks in medical diagnosis and image recognition using ReLU and sigmoid activations.