Foundations of AI and Deep Learning

This unit surveys the historical evolution from mechanical reasoning to modern generative AI, introduces core machine learning and deep learning concepts, and provides a focused deep dive on neural network architectures including transformers. It prepares learners to reason about model design and the practical considerations for running deep learning and GenAI workloads on AWS, forming the conceptual foundation for applied model development and deployment in later units.

Learning Objectives

• Analyze major historical milestones from mechanical reasoning through transformer-based generative AI and produce a timeline that links each era to contemporary capabilities and design trade-offs
• Compare machine learning, deep learning, and generative AI by distinguishing symbolic and subsymbolic approaches and summarizing representative algorithms and architectures in a concise written report
• Demonstrate understanding of neural network components and transformer architecture by diagramming common architectures (feedforward, CNN, RNN, transformer) and annotating data flow, parameters, and training considerations
• Evaluate practical considerations for running deep learning and generative AI workloads on AWS by identifying appropriate AWS services, scalability and cost factors, and ethical/security implications, and by producing a deployment checklist