Feed-forward neural network implementation in C with SIMD instructions

Keras Fully Connected Neural Network using Python for Digit Recognition

Double Descent results for FCNNs on MNIST, extended by Label Noise (Reconciling Modern Machine-Learning Practice and the Classical Bias–Variance Trade-Off) [Python/PyTorch]..

This repo contains my experiments with machine learning, specifically convolutional neural networks.

This is the code for a fully connected neural network. The code is written from scratch using Numpy, without using any ready-made deep learning library. In this, classification is done on the MNIST dataset. It is generalized to include various options for activation functions, loss functions, types of regularization, and output activation types.

Fully Connected Neural Network, Numpy, Computational graph

Fully Connected Forward Feed Neural Network

A fully connected linear neural network to recognize handwritten digits trained on the MNIST dataset

This repository contains a collection of fully connected benchmarks from VNNCOMP 2022-2024. It is designed to offer a more organized version of the existing benchmarks, making it easier to test new software. We recommend cloning the 'benchmarks_vnncomp' repository, which includes this repository as a submodule.

Implement GAN (Generative Adversarial Network) on MNIST dataset. Vary the hyperparameters and analyze the corresponding results.

Building fully connected neural network from zero without using deep learning libraries such as Pytorch.

Fully connected neural network diagnosing patients with diabetes.

Investigates which datasets different neural network implementations are useful

Unsupervised Learning Algorithms being implemented to detect a liar.

Predicts the critical heat flux by leveraging Pytorch's custom Datasets and DataLoaders and building curated models.

This GitHub repository contains the code used for CS-671: Introduction to Deep Learning course offered by IIT Mandi during the Even Semester of 2022. The repository includes the implementations of various deep learning algorithms and techniques covered in the course.