Introduction to AI Ethics & Safety (Pathways)

Description

Build productionready AI systems by mastering generative, multimodal, and agentbased models--from PyTorch fundamentals to LLM evaluation, RAG, and realworld deployment.

• EndtoEnd Generative and Multimodal AI Mastery
• Practical Evaluation, Optimization, and FineTuning of AI Systems
• ProductionReady AI Applications, Agents, and Developer Tooling

AI Engineer teaches the skills to design, build, evaluate, and deploy modern AI systems. Starting with essential foundations in AI ethics, safety, and generative modeling, learners progressively develop handson expertise in deep learning with PyTorch, diffusion and transformerbased models, and multimodal AI systems that combine text, images, and more. The course goes beyond model building to focus on realworld readiness, teaching learners how to evaluate LLMs, finetune models efficiently, implement retrievalaugmented generation (RAG), and build autonomous AI agents. By the end of the course, learners will be able to create productiongrade AI applications, confidently assess model performance and risks, and apply best practices for scalable, responsible, and enterpriseready AI development.

Skill Level

• Beginner to Intermediate

About Pearson Video Training

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Sams, and Que. Topics include: IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at http://www.informit.com/video.

Sample Content

Table of Contents

Module 1: AI Ethics and Safety

Lesson 1: AI Ethics

Lesson 2: AI Safety

Module 2: Programming Generative AI

Lesson 3: Generative AI Foundations

Lesson 4: PyTorch for the Impatient

Lesson 5: Latent Space and Autoencoders

Lesson 6: Diffusion Models

Lesson 7: Transformers and NLP

Lesson 8: Multimodal Models (Text + Image)

Lesson 9: Post-Training for Diffusion Models

Module 3: Evaluating Large Language Models (LLMs)

Lesson 10: Foundations of LLM Evaluation

Lesson 11: Evaluating Generative Tasks

Lesson 12: Evaluating Understanding Tasks

Lesson 13: Using Benchmarks Effectively

Lesson 14: Probing LLMs for a World Model

Lesson 15: Evaluating LLM Fine-Tuning

Lesson 16: Case Studies

Lesson 17: Summary and Future Trends

Module 4: AI-Enhanced Coding with Amazon Q Developer

Lesson 19: Lab Setup and IAM

Lesson 20: IDE Integration

Lesson 21: CLI and Assistant Usage

Lesson 22: General Usage in AWS Tools

Lesson 23: Enterprise Features

Lesson 24: Enterprise Demos

Lesson 25: Testimonials and Summary

Module 5: Multimodal AI Essentials

Lesson 26: Introduction to Multimodal AI

Lesson 27: Visual Question Answering (VQA)

Lesson 28: Diffusion Models

Lesson 29: Developing Multimodal Systems

Lesson 30: Evaluation and Ethics

Lesson 31: Future Trends

Module 6: Practical Retrieval-Augmented Generation (RAG)

Lesson 32: Introduction to RAG

Lesson 33: Building Foundations

Lesson 34: Prompt Engineering

Lesson 35: Developing RAG Systems

Lesson 36: Evaluation and Testing

Lesson 37: Expansion and GraphRAG

Module 7: Modern Automated AI Agents

Lesson 38: Introduction to AI Agents

Lesson 39: Under the Hood

Lesson 40: Building Agents

Lesson 41: Testing and Evaluation

Lesson 42: Planning and Reflection

Lesson 43: Advanced Applications

Lesson 44: Building Commercially Successful LLM Applications

Lesson 45: Agentic Artificial Intelligence

Updates

Submit Errata