Practical Generative AI: A Hands-On Introduction for Technical Professionals
Room: Room 205, Bldg: Becton Building , FDU Metropolitan Campus, 960 River Road, Teaneck, New Jersey, United States, 07666September 20 through November 1, 2025. Six Saturdays 1:30-4:30pm (9/20, 9/27, 10/4, 10/18, 10/25, 11/1). The IEEE North Jersey Section Communications Society Chapter is offering a course entitled "Practical Generative AI: A Hands-On Introduction for Technical Professionals". This six-week introductory course in Generative AI is designed for a technical audience with no prior specialization in AI or machine learning. It provides a practical, hands-on approach to understanding how generative models like large language models (LLMs) work and how they can be applied across tasks involving text, code, images, and video. The course begins with foundational concepts, including the evolution of generative AI, and moves into core mechanics such as tokenization, transformers, and prompt engineering. Participants explore both the capabilities and limitations of tools like ChatGPT, Google Gemini, GitHub Copilot, and various APIs. The course will include some suggested projects using freely tools such as Gemini and AWS. Each week combines a lecture with interactive demos and assignments to reinforce learning through real-world use cases. The latter weeks focus on building simple GenAI-powered apps and understanding limitations such as bias, hallucinations, and data privacy. The course wraps up with future directions in AI and equips participants with the skills to responsibly use and to integrate generative models into their own technical workflows. The IEEE North Jersey Section's Communications Society Chapter can arrange for providing IEEE CEUs - Continuing Education Units (for a $5 charge) upon completion of the course. Course prices: $75 for Undergrad/Grad/Life/ComSoc members, $100 for IEEE members, $150 for non-IEEE members. If paying by check, make payee out to "IEEE North Jersey Section". Co-sponsored by: Education Committee Speaker(s): Thomas Long, Agenda: Agenda: The primary objective of this course is to provide students with an understanding of Gen AI, tools and techniques used, the wide variety of applications, and an Agentic future. The material covered includes an introduction to the concepts and how to build applications using these concepts. On the completion of the course, students will learn: Week 1: Introduction to Generative AI Goal: Ground the audience in what Generative AI is, its evolution, and why it matters. Topics: History of generative models (GANs → Transformers), Multi-modal use cases, Overview of LLMs, Economics, and Regulatory landscape. Week 2: How Generative AI Works Goal: Demystify the architecture and inner workings of generative models. Topics: Review of deep neural networks and core ideas like: tokenization, embeddings, attention, transformers, how to train an LLM. What is the differences between Fine-tuning vs. pretraining vs. prompt engineering, and how to deal with hallucinations, biases, context windows Week 3: Building with Generative AI APIs Goal: Equip learners to integrate LLMs into real-world apps. Topics: What are the key APIs available to use (OpenAI, Google Gemini, AWS, HuggingFace), Using and calling models with Python, Building a simple GenAI-powered app (chatbot) and what is prompt templating and chaining Week 4: Prompt Engineering for Developers Goal: Learn effective prompting strategies for real-world applications. Topics: Different types include Zero-shot, few-shot, chain-of-thought prompting, Common prompt engineering mistakes, System messages and role prompts, and Code generation with LLMs (Copilot, Gemini+Colab, GPT-4) Week 5: Image & Video Generation Goal: Broaden the view beyond text; explore image and video synthesis. Topics: How to do image generation using diffusion models (DALL·E, Midjourney, Stable Diffusion) How to do video generation using Google Veo Week 6: Generative AI Agents and Autonomous Workflows Goal: Introduce AI agents, their architecture, and how they orchestrate autonomous tasks using LLMs. Topics: What are AI agents and how to agents use tools, memory, and planning. Real world use cases: research assistants, workflow automation, task chaining Risks and guardrails: failure cases, cost, ethical boundaries, and what is AGI and the alignment problem? Technical Requirements : Access to a tool such as ChatGPT or Google Gemini will be necessary to complete most examples using prompts. Coding demos in this course will use the Python programming language and will be distributed in the form of Colab notebooks. During the latter portion of the course, coding demos will make use of the Google Gemini APIs. These examples can easily be adapted to other frameworks such OpenAI APIs, etc. Basic programming skills and some familiarity with the Python language are assummed. Students are expected to be able to bring a laptop in order to use Google Colab Notebooks. The course is intended to be subdivided into six sessions, each three hours long for a total of 18 course hours. Each lecture is further subdivided into lecture, guided and independent project based exercises to build experience with hands-on techniques. CEUs will be made available. This course will be held at FDU - Teaneck, NJ campus. Checks should NOT be mailed to this address. Can physically bring (preferred) checks in person on the first day or use online payments at registration. Email the organizer for any questions about course, registration, or other issues. Room: Room 205, Bldg: Becton Building , FDU Metropolitan Campus, 960 River Road, Teaneck, New Jersey, United States, 07666