Deeper Networks for Image Classification

This is an analysis of Convolutional Neural Networks (CNNs) on the MNIST and CIFAR10 datasets. The project evaluates the performance of four models: InceptionV3, VGG16, ResNet50, and MobileNetV2
I'm Kaviraj Gosaye, an Artificial Intelligence enthusiast specializing in Computer Vision and Robotics.
Masters at Queen Mary University of London
Recipient of the Google DeepMind Scholarship
Specialization in Vision and Robotics
Classification: Distinction
Bachelors at the University of Mauritius
Classification: First Class with Honours
Deep Learning Short Course organised by UoM and HRDC with guest Dr Wilie Brinks from University of Stellenboch
First Level of the British Computer Society Exam
Modules: Infomation Systems, Software Development, Computer and Network Technology
A-Levels at Mahatma Gandhi Institute Moka
Ranked 420th on the Mauritius Top 500 Order List
Main Subjects: Computer Science, Mathematics, Physics
Subsidiary: French, General Paper
O-Levels at Mahatma Gandhi Institute Moka
Subjects: English, Maths, Add Maths, French, Hindi, Computer Studies, Chemistry
Python
PyTorch
Scikit-Learn
MLflow
Keras
TensorFlow
ROS
OpenCV
Git
Java
MySql
C#
This is an analysis of Convolutional Neural Networks (CNNs) on the MNIST and CIFAR10 datasets. The project evaluates the performance of four models: InceptionV3, VGG16, ResNet50, and MobileNetV2
Vision Toolkit is a project showcasing various basic computer vision tools. The toolkit includes: 1. Image Rotation, 2. Convolution and Filters, 3. Color Histogram, 4. Similarity Descriptor, 5. Background Extractor
This project is an AI route finder for the London Tube using an agenda-based search mechanism. It implements and compares four algorithms: 1. Breadth-First Search (BFS), 2. Depth-First Search (DFS), 3. Uniform Cost Search (UCS), 4. Best-First Search (Heuristic Search)
ROS package simulates an experiment to test if great apes can anticipate human false beliefs using a Bayesian network.
A Flutter mobile application that allows identification of fruit flies using Deep Learning.
An automatic seeding machine that makes use of a rover, a robot arm and sensors. This project won the first prize in UoM Hackathon 2020 and was presented for UoM Robotics Lab launching ceremony.
Winner of the UoM Web Competition in 2019. A website had to be developed in 24hrs from scratch.
A 48 hour competition organised by the MCB where ideas are developed and pitched.
A 24 hour competition to develop a mobile application related to the SDGs.
Winner of the 3-days long competition to develop an innovative solution on the topic of Agriculture.