Course
Artificial Intelligence
45 hours 14 minutes
Credits: 3 Credits
Description
This course teaches learners how to understand, develop, and architect artificial intelligence solutions across a broad range of frameworks, tools, and application areas. Starting from AI developer and architect fundamentals, learners progress through generative AI APIs, neural network engineering with PyTorch and Transformers, LLM integration and evaluation, RAG application development, Streamlit deployment, and building AI agents with LangChain, culminating in a capstone project.
What Students Will Learn
Chapter 1: AI Developer
- AI Framework Overview: AI Developer Role
- AI Framework Overview: Development Frameworks
- Working With Microsoft Cognitive Toolkit (CNTK)
- Keras - a Neural Network Framework
- Introducing Apache Spark for AI Development
- Implementing AI With Amazon ML
- Implementing AI Using Cognitive Modeling
- Applying AI to Robotics
- Final Exam: AI Developer
Chapter 2: AI Architect
- Elements of an Artificial Intelligence Architect
- AI Enterprise Planning
- AI in Industry
- Leveraging Reusable AI Architecture Patterns
- Evaluating Current and Future AI Technologies and Frameworks
- Explainable AI
- Final Exam: AI Architect
Chapter 3: Fundamentals of Generative AI APIs
- Generative AI APIs for Practical Applications: An Introduction
Chapter 4: Harnessing OpenAI APIs for Powerful Application Solutions
- Introduction to the OpenAI API
- Text, Image, & Audio Generation with OpenAI
- Code, Relatedness, & Fine-tuning with OpenAI
Chapter 5: Engineer Neural Networks with PyTorch and Transformers
- Introduction to Neural Network Architectures
- Introduction to Neural Network Architectures Lab: Build Neural Networks for Classifying Digits and Time-Series Predictions
- Advanced Neural Network Architectures
- Advanced Neural Network Architectures Lab: Classifying CIFAR-10 with Pretrained CLIP
- Transformers: The "T" in GPT
- Exploring Transformers with Hugging Face
- Exploring Transformers Lab: Exploring Their Carbon Footprint
- Introduction to Finetuning
- Engineer Neural Networks Lab: Classifying Banking Intent from Customer Queries
Chapter 6: Integrate and Evaluate LLMs
- OpenAI API
- OpenAI API with Python
- OpenAI Python API Lab: Recipe Blog
- An Introduction to LLM Evaluation
- Using Benchmark Datasets for Evaluating LLMs
- LLM Benchmarking and Evaluation Lab: Benchmarking LLMs on Multiple NLP Tasks
Chapter 7: Build AI-Powered Applications with Streamlit and RAG
- Build AI Applications with Streamlit
- Build AI Applications with Streamlit Lab: Build an AI Image Classification Dashboard with Streamlit
- RAG Foundations
- Build a RAG App
- RAG Techniques
- Best Practices in AI Deployment
- Best Practices in AI Deployment Lab: Analyzing Recommendation System Performance Across Model Versions
Chapter 8: Build AI Agents with OpenAI and LangChain
- Introduction to Agents Skillshort
- Getting Started with LangChain
- LangChain Lab: Mini Quiz Generator
- AI Agents and Workflows
- AI Agents and Workflows Lab: Building an Agentic Meal Planner
- Augmented LLMs for AI Agents
- Augmented LLMs Lab: Building an Augmented Writing Assistant
Chapter 9: Capstone Project: Build an AI Agent for Travel Planning
- Capstone Project: Build an AI Agent for Travel Planning
Optional
- Introduction to Neural Network Architectures Cheatsheet
- Advanced Neural Network Architectures Cheatsheet
- Transformers: The "T" in GPT Cheatsheet
- Exploring Transformers with Hugging Face Cheatsheet
- Introduction to Finetuning Cheatsheet
- OpenAI API Cheatsheet
- OpenAI API with Python Cheatsheet
- An Introduction to LLM Evaluation Cheatsheet
- Using Benchmark Datasets for Evaluating LLMs Cheatsheet
- RAG Foundations Cheatsheet
- Build a RAG App Cheatsheet
- RAG Techniques Cheatsheet
- Build AI Applications with Streamlit Cheatsheet
- Best Practices in AI Deployment Cheatsheet
- Introduction to Agents Skillshort Cheatsheet
- Getting Started with LangChain Cheatsheet
- AI Agents and Workflows Cheatsheet
- Augmented LLMs for AI Agents Cheatsheet
- NLP Case Studies: Article Text Comprehension & Question Answering
- NLP Case Studies: Developing an AI Chatbot
- Generating Text With Deep Learning Cheatsheet
- Bag Of Words Language Model Cheatsheet
- Introduction to Regular Expressions Cheatsheet
- Word Embeddings Cheatsheet
- Getting Started with NLP Cheatsheet
- Text Preprocessing with NLTK Cheatsheet
Overall Learning Outcomes
- Explain AI developer and architect roles, enterprise planning, and reusable AI architecture patterns across industries
- Work with AI development frameworks including CNTK, Keras, Apache Spark, and Amazon ML
- Apply explainable AI principles and evaluate current and future AI technologies
- Build applications using Generative AI and OpenAI APIs for text, image, audio, and code generation
- Engineer and fine-tune neural network architectures using PyTorch and Transformer models
- Use Hugging Face for transformer exploration, tokenization, and model fine-tuning
- Integrate and evaluate LLMs using OpenAI and Hugging Face benchmark datasets
- Build AI-powered applications and dashboards using Streamlit
- Design and implement RAG applications using foundational and advanced retrieval techniques
- Apply AI deployment best practices and analyze model performance
- Build AI agents and agentic workflows using LangChain and augmented LLMs
- Demonstrate end-to-end AI development skills through a capstone travel planning agent project