Summary of Machine Learning and Deep Learning Assignments
📂 Source code unavailable due to course material restrictions.
This post summarizes several assignments I completed as part of my coursework in machine learning and deep learning. These assignments mainly consist of Jupyter notebooks focused on practical implementations and comparative analyses of various algorithms.
Key Assignments
-
Comparison of Naïve Bayes Classifier and Logistic Regression Implemented Naïve Bayes Classifier (NBC) from scratch and compared its performance with logistic regression across multiple datasets.
-
Open Set Recognition with Neural Networks Trained a network capable of classifying known classes while effectively rejecting unknown samples.
-
Convolutional Network Training on FashionMNIST Built and trained convolutional neural networks for image classification tasks on the FashionMNIST dataset.
-
Transfer Learning with Pre-trained Networks Applied transfer learning techniques using pre-trained models based on ImageNet to new classification tasks.
-
Convolutional Auto-encoder Implementation Designed and trained convolutional auto-encoders for unsupervised feature learning and data reconstruction.