This project involved a comprehensive analysis comparing Support Vector Machine (SVM) kernels against a Feedforward Neural Network (MLP) baseline for multi-class image classification on the CIFAR-10 dataset. The implementation included two distinct SVM methods: a non-linear RBF Kernel requiring Principal Component Analysis (PCA) for dimensionality reduction (achieving 43.91% Test Accuracy), and a Linear Kernel baseline (achieving 35.48% Test Accuracy). All models were implemented using Scikit-Learn and TensorFlow for data handling. The extensive experimentation documented the significant performance gap between kernels, highlighting the inability of linear models to capture complex image features and the superiority of non-linear mapping for visual data.

View on GitHub

This project involved a comprehensive analysis comparing different Feedforward Neural Network (FNN) architectures for multi-class image classification on the CIFAR-10 dataset. The implementation included two distinct methods: an MLP Baseline requiring Principal Component Analysis (PCA) for dimensionality reduction (achieving 52.88% Test Accuracy), and a Convolutional Neural Network (CNN) (achieving 70.00% Test Accuracy). All models were trained using the Back-propagation algorithm with the Adam optimizer. The extensive experimentation documented Overfitting in both architectures, highlighting the critical need for regularization and Early Stopping in production models

View on GitHub

This project involved the design and implementation of a custom unsupervised learning pipeline to address clustering and outlier detection challenges in corrupted datasets. The architecture combined defensive data pre-processing with a novel Iterative K-Means algorithm. This approach leveraged a core-filtering technique—training exclusively on the closest 30% of points to the initial centers—to refine centroid detection and ensure they were not shifted by noise. Developed using Python, Pandas, and Scikit-Learn , the implementation highlighted the effectiveness of isolating noise prior to final classification. Project was developed by team of three.

View on GitHub