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.

This repository contains code that implemented Mask Detection using MobileNet as the base model and Neural Network as the head model. Code draws a rectangular box over the person's face in red if no mask, green if the mask is on, with 99% accuracy in real-time using a live webcam. Refer to README for demo

CS 182 Spring 2019 - Assignment 1

This repository contains various networks implementation such as MLP, Hopfield, Kohonen, ART, LVQ1, Genetic algorithms, Adaboost and fuzzy-system, CNN with python.

Explain fully connected ReLU neural networks using rules

Neural Networks Classification on Fashion MNIST.

Application of Fully Connected Neural Networks (FCNs) & Graphical Convolutional Neural Networks (GCNs) using pytorch to fmri movie data

Using different ML models with different optimizers (pytorch)

BlessMark: A Blind Diagnostically-Lossless Watermarking Framework for Medical Applications Based on Deep Neural Networks

MNIST handwritten digit classification using PyTorch

My projects from the Udacity Deep Learning Nanodegree.

This projects constructs the fully connected layered (MLP)neural network models to predict the cardio vascular disease in the patient.To validate the models constructed, an ensemble method (using the voting) is implemented.

RoboND Term 1 Deep Learning Project, Follow-Me

Implemented fully-connected DNN of arbitrary depth with Batch Norm and Dropout, three-layer ConvNet with Spatial Batch Norm in NumPy. The update rules used for training are SGD, SGD+Momentum, RMSProp and Adam. Implemented three block ResNet in PyTorch, with 10 epochs of training achieves 73.60% accuracy on test set.