CoursesMachine Learning
Machine LearningAdvancedSelf-paced
Building AI Applications with Foundation Models
This course covers the development and engineering of AI applications using foundation models, including evaluation methodologies, prompt engineering, fine-tuning, and optimization techniques. It is designed for learners looking to apply AI and machine learning principles in practical applications. The course delves into advanced topics such as dataset engineering and inference optimization.
59chapters
200modules
443lessons
89quizzes
Syllabus
59 chapters, 200 modules, 532 lessons and quizzes.
01Getting Started1 modules · 3 lessons
02Evolution of AI: From Language Models to Engineering3 modules · 10 lessons
Understanding Language Models
Self-Supervision and Scaling of Language Models
From Foundation Models to AI Engineering
03Foundation Model Applications9 modules · 15 lessons
Enterprise Willingness to Adopt LLMs
Coding Applications
Creative Tasks and Advertising
Writing Assistance
Education and Learning
Conversational Bots
Information Aggregation and Organization
Workflow Automation
04Strategic Planning for AI Applications2 modules · 8 lessons
Evaluating AI Use Cases
Designing AI Applications
05Building and Maintaining Competitive AI Products3 modules · 6 lessons
Creating Defensible AI Products
Planning for Success
06Model Adaptation through Finetuning1 modules · 3 lessons
07Evaluating Model Performance2 modules · 4 lessons
Understanding Evaluation
08Designing Interfaces for AI Applications3 modules · 11 lessons
Types of Interfaces for AI Applications
Comparing AI Engineering and Traditional Full-Stack Development
10Foundation Models and Emerging Applications3 modules · 9 lessons
Evolution of Foundation Models
Adapting Foundation Models for Specific Applications
Considerations for Building Applications
11Designing Language Models2 modules · 10 lessons
Model Architecture Fundamentals
Model Size and Compute Requirements
12Refining Pre-Trained Models for Conversational AI3 modules · 10 lessons
Introduction to Post-Training
Supervised Finetuning
13Foundation Model Design and Usage3 modules · 8 lessons
Understanding Foundation Models
Model Architecture and Scaling
14Evaluating Foundation Models: Challenges and Limitations2 modules · 6 lessons
Challenges in Evaluating Sophisticated Models
15Evaluating Language Model Performance6 modules · 8 lessons
Information Theory Basics
Cross Entropy and Model Evaluation
Alternative Metrics for Language Models
Perplexity and Its Applications
Interpreting Perplexity
Computing Perplexity
16Evaluating Model Performance with Precision3 modules · 11 lessons
Assessing Functional Correctness
Comparing Generated Responses to Reference Data
17Evaluating AI Responses with AI Judges4 modules · 10 lessons
Introduction to AI Judges
Using AI as a Judge
Limitations of AI Judges
18Comparative Evaluation for Model Ranking3 modules · 8 lessons
Understanding Comparative Evaluation
Challenges in Comparative Evaluation
The Future of Comparative Evaluation
19Evaluating Foundation Models4 modules · 6 lessons
Challenges in Evaluating Foundation Models
Language Modeling Metrics
Evaluating Open-Ended Responses
Advanced Evaluation Topics
20Assessing AI Application Effectiveness5 modules · 11 lessons
Evaluation-Driven Development
Domain-Specific Capabilities
Generation Capability
Instruction-Following Capability
21Crafting Effective Evaluation Pipelines4 modules · 14 lessons
Evaluating Complex AI Systems
Creating Evaluation Guidelines
Defining Evaluation Methods and Data
22Building a Reliable Evaluation Pipeline3 modules · 7 lessons
Evaluation Pipeline Fundamentals
Evaluating Foundation Models
23Crafting Effective Prompts for Foundation Models4 modules · 12 lessons
Understanding Prompts and Their Components
In-Context Learning and Prompt Engineering
System and User Prompts
24Effective Prompt Engineering Strategies1 modules · 5 lessons
25Optimizing Model Responses4 modules · 12 lessons
Crafting Effective Prompts
Task Decomposition and Chain-of-Thought Prompting
Iterating on Prompts and Using Prompt Engineering Tools
26Effective Communication with Foundation Models3 modules · 7 lessons
Crafting Effective Prompts
Security Considerations
Providing Context
27Protecting Applications from Malicious Attacks5 modules · 12 lessons
Understanding Prompt Attacks
Proprietary Prompts and Reverse Prompt Engineering
Jailbreaking and Prompt Injection
Information Extraction
Defenses Against Prompt Attacks
28RAG vs Long Context: Choosing the Right Approach1 modules · 3 lessons
29Retrieval-Augmented Generation Systems2 modules · 5 lessons
RAG System Fundamentals
Terminology Clarification
30Information Retrieval Techniques7 modules · 12 lessons
Retrieval Algorithm Fundamentals
Sparse vs Dense Retrieval
Term-Based Retrieval
Embedding-Based Retrieval
Vector Search Algorithms
Evaluating Retrieval Algorithms
31Optimizing Information Retrieval5 modules · 12 lessons
Chunking Strategies for Effective Retrieval
Improving Retrieval Accuracy through Reranking
Rewriting Queries for Better Retrieval
Contextual Retrieval Techniques
Evaluating Retrieval Solutions
32Advanced RAG Techniques2 modules · 5 lessons
Multimodal RAG Systems
33Understanding Memory in Models5 modules · 9 lessons
Memory Mechanisms
Memory Hierarchy and Applications
Persisting Information and Model Consistency
Maintaining Data Structural Integrity
34Generating Outputs with AI Models6 modules · 18 lessons
Understanding Sampling Fundamentals
Logits and Softmax Transformation
Sampling Strategies
Test Time Compute and Output Selection
Structured Outputs
35Retrieval-Augmented Generation and Agents3 modules · 9 lessons
Understanding RAG and its Components
Understanding Agents
36Mastering Model Finetuning3 modules · 7 lessons
Introduction to Finetuning
Finetuning Techniques
37Finetuning and Model Optimization Techniques5 modules · 6 lessons
Finetuning Fundamentals
Parameter-Efficient Finetuning Techniques
Model Merging and Optimization
Memory Calculation and Numerical Formats
Instruction Finetuning and Alignment
38Shifting Focus to Data in AI Development2 modules · 5 lessons
Understanding Model-Centric and Data-Centric AI
39Curating Data for Model Training5 modules · 9 lessons
Teaching Models Complex Behaviors
Data Quality
Data Coverage and Diversity
Determining Data Quantity
40Generating Data for AI Model Training3 modules · 11 lessons
Traditional Data Synthesis Techniques
Understanding Data Augmentation and Synthesis
Why Data Synthesis is Useful
- LessonIncreasing Data Quantity: How Synthesis Adds Volume to Training DataEnroll to open
- LessonImproving Data CoverageEnroll to open
- LessonEnhancing Data Quality: When Synthetic Data Beats Human DataEnroll to open
- LessonMitigating Privacy Concerns with Synthetic DataEnroll to open
- LessonModel Distillation: Training a Model to Imitate AnotherEnroll to open
- QuizData Synthesis Benefits QuizEnroll to open
41Effective Data Preparation for AI Models4 modules · 11 lessons
Understanding and Inspecting Your Data
Removing Duplicate Data
Cleaning and Filtering Data
42Effective Dataset Design for AI Models2 modules · 7 lessons
Principles of Dataset Design
Synthetic Data and Model Improvement
43Inference Fundamentals and AI Accelerators3 modules · 12 lessons
Inference Fundamentals
Inference Performance Metrics
AI Accelerators for Inference
44Building AI Applications: Layers and Engineering Disciplines2 modules · 7 lessons
Understanding the AI Application Stack
45Crafting Effective Training Data3 modules · 11 lessons
The Impact of Training Data Quality
Multilingual Models and Language Representation
46Mastering Dataset Engineering2 modules · 6 lessons
Understanding Dataset Engineering
47Selecting the Right Model for Your Application3 modules · 10 lessons
Understanding Model Selection
Model Build Versus Buy Decision
Navigating Public Benchmarks
48Inference Optimization Techniques3 modules · 6 lessons
Understanding Efficiency Metrics
Inference Service-Level Optimization
Model-Level Optimization Techniques
49Deciding When to Finetune Models5 modules · 12 lessons
Reasons for Finetuning
Reasons Against Finetuning
Finetuning for Domain-Specific Tasks
Finetuning and RAG
Application Development Workflow
50Why Inference Optimization Matters3 modules · 8 lessons
Understanding Inference Optimization
Application Development with Foundation Models
Techniques for Inference Optimization
51Optimizing Inference for Efficient AI Systems2 modules · 10 lessons
Model-Level Optimization Techniques
- LessonModel Compression Techniques: Making Models Smaller and FasterEnroll to open
- LessonOvercoming Autoregressive Decoding BottleneckEnroll to open
- LessonOptimizing the Attention MechanismEnroll to open
- LessonKernel Writing for Efficient Attention ComputationEnroll to open
- QuizModel-Level Optimization QuizEnroll to open
Service-Level Optimization Techniques
- LessonBatching Techniques for Inference ServicesEnroll to open
- LessonDecoupling Prefill and Decode for Efficient InferenceEnroll to open
- LessonPrompt Caching for Reducing Latency and CostEnroll to open
- LessonParallelism Strategies for Inference ServicesEnroll to open
- LessonService-Level Optimization Practice: Batching, Caching, and CostEnroll to open
52Understanding and Mitigating Memory Constraints3 modules · 11 lessons
Memory Bottlenecks and Trainable Parameters
Calculating Memory Requirements
Numerical Representations and Quantization
53Efficient Model Adaptation Techniques4 modules · 12 lessons
Understanding Parameter-Efficient Finetuning
Model Merging and Multi-Task Finetuning
Practical Finetuning Strategies
54Designing AI Application Architectures7 modules · 23 lessons
Simple Architecture and Context Enhancement
Implementing Guardrails
Model Router and Gateway
Caching Mechanisms
Complex Application Architectures and Agentic Patterns
Monitoring and Observability
55Intelligent Agents and Their Capabilities4 modules · 9 lessons
Introduction to Intelligent Agents
Tools for AI-Powered Agents
Planning in AI-Powered Agents
56Synthetic Data Generation Techniques7 modules · 14 lessons
Rule-Based Data Synthesis
Simulation-Based Data Synthesis
AI-Powered Data Synthesis
Instruction Data Synthesis
Data Verification and Quality Control
Limitations of AI-Generated Data
57Leveraging User Feedback for AI Applications3 modules · 9 lessons
Understanding User Feedback
Extracting Conversational Feedback
58Collecting and Understanding User Feedback2 modules · 8 lessons
Effective Feedback Collection
59Building AI Applications on Foundation Models2 modules · 6 lessons
Understanding AI Application Architecture
60Future of AI Development1 modules · 3 lessons
Growing Applications and Systematic Approaches
Start Building AI Applications with Foundation Models today.
Listed at ₹12,999. Free for you right now.
Building AI Applications with Foundation Models