Back to Projects
Machine LearningNumPyClassificationCoursework
Spam Detection — Logistic Regression & Neural Network (CW2)
Binary spam classification from word-count features: NumPy implementations of logistic regression and a ReLU hidden-layer network, with training curves and comparisons.
Year: 2025Category: Machine Learning
Project Overview
Coursework portfolio: implements spam vs non-spam prediction using 10 word-count features. Logistic regression uses gradient descent on cross-entropy; the neural network uses a 15-unit ReLU hidden layer trained with backpropagation. All code is NumPy and Matplotlib only, with figures for weights, losses, and predictions. See the report for methodology and results; source code can be published separately on GitHub.