Foundations of TensorFlow and ML

This unit introduces core machine learning concepts and the TensorFlow ecosystem, including installation, tensor creation, graph execution, and basic model building. Students will explore fundamental algorithms (linear regression, perceptrons), dataset selection and preprocessing, and introductory image filtering and convolutional neural network concepts to prepare for deeper model development in subsequent units.

Learning Objectives

• Analyze foundational machine learning concepts and the historical development of ML to distinguish supervised, unsupervised, and neural approaches
• Apply TensorFlow installation procedures and environment configuration to create, run, and debug basic TensorFlow programs on a local machine
• Demonstrate creation and manipulation of tensors, graphs, and sessions, and implement simple models including linear regression and a single-layer perceptron
• Evaluate dataset selection, preprocessing, and model-improvement techniques (including basic image filtering and CNN concepts) to propose refinements that improve model performance