This model develops an accurate system for classifying retinal images to assist in early detection and management of eye conditions.

This project focuses on the task of image classification using datasets sourced from Kaggle. The primary goal of this repository is to evaluate the performance of two neural network architectures, AlexNet and VGG16, and to draw comparisons between these methods.

This Archieve will have models architectures

CNN class with alexnet, VGG-net and Resnet-34 architectures

Python code for Neuromatch Academy's Summer 2021 Computational Neuroscience final project, exploring the correspondence between Alexnet layers and visual cortex hierarchy using fwRF encoding models and fMRI response prediction.

Page with angular to visualize pathogens found in plants with convolutional neural networks.

Apply machine learning to find top 10 similar images from a gallery folder given a query image.

Code and reports of the two homework for the Machine Learning course (Winter 2020)

AlexNet Model Testing In A Vast Dataset for Kurdish Digits and Isolated Characters Recognition

Implementation of LeNet-5, AlexNet, VGG-16 as explained by Andrew NG in Deeplearning.AI

We will use the Convolutional Neural Networks, to classify the cancer cells into Normal and Cancer cells. Two custom models and two models on transfer learning.

A 10-way Pokemon Classification using Deep Learning

Through the AlexNet and VGG16 convolutional networks, the neural networks were trained on a set of 600 spatial spectrogram images divided into 3 categories and divided into train, test, validation test

Designed a robotic system using inference. Created a project idea, collected data set for classification, and justified network design choices based on technical analysis of accuracy and speed on the target system.

Tools : CUDA C, Multicore Programming, Batch Scripting, MATLAB

ILSVRC 2012 classification playground