Russell Ho's repositories
Vision-Transformer
Implementation of Vision Transformer (ViT) model for image classification on a custom dataset (the pyCOCO dataset). The model leverages the power of the transformer architecture to classify images into 5 different categories
Generative-Adversarial-Network-Pizzas-
A generative adversarial network engineered that utilizes a discriminator and a generator. The GAN can be trained using a Binary Cross Entropy Loss or a Wasserstein Distance Loss to generate replicate images based on input data.
CNN-Computer-Vision-Model-Analysis
This model was designed around Pycoco's dataset, the CNN model constructed outputs training loss graphs and a confusion matrix for the network of interest
Cochlear-Implant-Project
MATLAB code for Cochlear Implant Project that aims to explore the nuances of speech-to-speech, melody-to-melody signal processing.
Coding-step-size-optimizers
Manually hand-coding in step-size optimizers (momentum and Adam) for deep learning neural networks
Computer-Vision-ResNet-Object-Detector
Residual Neural Network Object Detector written for Pycocotool's library. Model implements custom skip block connections and uses a custom dataset loader for image classification object detection.
Electric-City-Full-Stack-Web-Platform
Full Stack Web Platform developed for EV Charging Service Strategic Entrepreneurship
Grade-Report-A.I.
Program that can take in large amounts of .csv files in the same directory and trains a deep learning neural network model based on the best/worst students evaluated by the user. Second program then utilizes the model from the first program to produce a projected report for each individual student inputted.
Personal-Assistant-AI-Friday
An Angular Web Application that utilizes ChatGPT and Google's API to create a voice-controlled virtual assistant
pokemon-contest
Pokemon Classification Contest
Principal-Component-Analysis-and-Fitting-Linear-Models
The MATLAB code written in the 3 files correspond to fitting linear models/testing the fitted model with independent datasets and Principal Component Analysis on Imported Datasets written in MATLAB. Each of the 3 files were written in accordance to assignment specifications
Sentiment-Analysis-with-GRU
This repository contains three variants of a Sentiment Analysis model that uses a GRU (Gated Recurrent Unit) to predict the sentiment of a given text as either positive or negative. The models were built using PyTorch, and the training and testing data came from DLStudio
Stock-Market-Application
Stock Market App Project
Typeracer-Project
This program utilizes the Selenium library to automate the playing of the online game Typeracer. Running the program will open the Google Chrome browser and start a new session as a guest for Typeracer.