Foundations of TensorFlow and ML

This unit introduces core machine learning principles and the TensorFlow ecosystem, including installation, basic APIs, and fundamental data constructs. Students will work with tensors, computational graphs, sessions, simple models (linear regression and perceptrons), dataset selection, and introductory image processing to prepare for deeper model development in subsequent units.

Learning Objectives

• Analyze foundational machine learning concepts and the historical development of the field, differentiating supervised and unsupervised approaches, perceptrons, neurons, and the role of CNNs.
• Apply TensorFlow installation and verification procedures, configure a development environment, and execute simple multi-threaded runs and estimator-based workflows.
• Demonstrate creation and manipulation of tensors, construction of computational graphs, and execution of sessions, including creating tensors with known values and running basic tensor operations.
• Evaluate and implement basic modeling and data workflows by selecting representative datasets, fitting and improving linear regression models, and applying elementary image filtering and CNN concepts.