Hello, I'm
Machine Learning Masters Student | Fulbrighter
I am a high-performing Fulbright Masters student with a background in Computer Engineering and am currently studying further in the Machine Learning domain. I have experience with embedded system engineering, high-level software development, robotics and computer vision.
A selection of university, industry and personal projects I have completed individually or contributed to
This individual capstone project involved the design and construction of a robotic system to construct arbitrary structures by stacking small cubes. The system featured a computer vision system to intelligently handle dropped and missing cube events during construction and an OpenGL-based structure design interface. The project won the Best Electrical, Electronic and Computer Engineering Capstone Project award at the University of Pretoria.
Visual odometry (VO) is the process of determining the position and orientation of a robot by analyzing the associated camera images. VO can be used to estimate the pose of drone for a given flight path. However, for long flights, the pose estimate can drift substantially from the true drone pose due to the accumulation of small errors at each time step. This project uses linear, MLP and LSTM machine learning models to correct for this drift.
This team project involved the development of a Convolutional Neural Network (CNN) using PyTorch with a custom architecture to classify American Sign Language fingerspelling images. Furthermore, the use of transfer learning from the ImageNet dataset was also explored with the GoogLeNet and ResNet18 architectures.
A Multilayer Perceptron (MLP) is a fully-connected feedforward artificial neural network which can be used for multi-class classification. This project contains a MLP implemented using only the NumPy library and applied to the MNIST dataset of handwritten digits. A final accuracy of 98.29% was obtained on the test set.
Softmax regression is a generalization of logistic regression to the multiclass case. This project contains a softmax regression model implemented using only the NumPy library and applied to the MNIST dataset of handwritten digits. A final accuracy of 92.09% was obtained on the test set.
Transfer pricing is an accounting practice that allows for the establishment of prices for the goods and services exchanged between legal entities of the same consolidated group. I developed the in-house desktop software platform for a transfer pricing advisory firm across a period of four years. The software facilitated the management of sensitive financial data for several multinational companies in conjunction with automated document generation. The desktop application was written using a combination of Java and Javascript and makes use of a MySQL cloud database hosted on Microsoft Azure.
Essentially, as a university student, Christopher developed a program that competes with a specific solution of the largest accounting firms in the world... Christopher has exceptional ability, a passion for excellence and an aptitude to learn extremely complex concepts in a short period of time.
