Applied Machine Learning (CS 460)

About This Course

Welcome to Applied Machine Learning, a comprehensive undergraduate course designed specifically for Bachelor of Computer Science students. This course provides a highly practical, hands-on introduction to the concepts, tools, and techniques required to build intelligent systems. We bridge the gap between foundational theory and production-ready implementation. The curriculum is structured into two main parts: the first covers machine learning fundamentals using Scikit-Learn, while the second dives deep into neural networks and deep learning using TensorFlow 2 and Keras.

What You Will Learn

In this course, you will actively build and train models rather than just studying theoretical mathematics. Through concrete examples and programming labs, you will master:

• The Machine Learning Landscape: Understanding supervised vs. unsupervised systems, classification vs. regression, and the workflow of a typical end-to-end ML project.
• Fundamental Algorithms: Implementing Linear and Polynomial Regression, Support Vector Machines (SVMs), Decision Trees, and Ensemble methods like Random Forests.
• Data Preparation & Feature Engineering: Mastering data cleaning, handling categorical attributes, feature scaling, and building robust transformation pipelines.
• Dimensionality Reduction & Unsupervised Learning: Applying PCA and unsupervised techniques such as clustering (K-Means, DBSCAN) and anomaly detection.
• Deep Learning & Neural Networks: Building, training, and fine-tuning Multilayer Perceptrons (MLPs) using the Keras Sequential, Functional, and Subclassing APIs.
• Advanced Deep Learning Architectures: Implementing Convolutional Neural Networks (CNNs) for computer vision, Recurrent Neural Networks (RNNs) for sequence processing, and Transformers for natural language processing.
• Generative Models & Reinforcement Learning: Exploring Autoencoders, Generative Adversarial Networks (GANs), and reinforcement learning fundamentals.

Why Take This Course?

Machine learning is no longer a futuristic concept; it is a core competency for modern computer science graduates. This course is uniquely designed to give you production-ready skills. Instead of building toy algorithms, you will work with powerful Python frameworks that power real-world applications at tech giants like Google. You will gain intuitive engineering insights and practical troubleshooting habits—such as hyperparameter tuning and error analysis—which are crucial for any aspiring machine learning engineer or data scientist.

Who Should Take This Course?

This course is tailored for upper-level Bachelor of Computer Science students who wish to specialize in AI and data science.

• Prerequisites: You must have solid Python programming experience and familiarity with its scientific libraries, particularly NumPy, pandas, and Matplotlib.
• Mathematics: A reasonable understanding of college-level math—including linear algebra, calculus, probabilities, and statistics—is highly recommended to understand what is happening under the hood.
• How to Succeed: To get the most out of this course, you must actively code along. You are expected to complete the hands-on coding labs using Jupyter notebooks to build your personal ML portfolio.