AI+ Developer Practitioner™

Štruktúra kurzu

Táto časť nie je lokalizovaná

Module 1: Foundations of Modern AI for Developers

• 1.1 Understanding Artificial Intelligence
• 1.2 Components of an AI Application
• 1.3 Beginner AI Development Workflow
• 1.4 AI Development Concepts and Limitations
• 1.5 Case Study: A Chatbot Prototype That Produced Unreliable Answers
• 1.6 Use Case: Selecting the Right AI Approach

Module 2: Python Programming for AI

• 2.1 Python Foundations
• 2.2 Python Data Structures and File Handling
• 2.3 Beginner Software-Development Practices
• 2.4 Case Study: An Unstructured Python Script Becomes Difficult to Maintain
• 2.5 Use Case: Automated File Processing Utility

Module 3: Data Handling and Visualization

• 3.1 Working with NumPy and Pandas
• 3.2 Data Cleaning
• 3.3 Exploratory Data Analysis
• 3.4 Case Study: Dirty Customer Data Produces Incorrect Sales Insights
• 3.5 Use Case: Retail Sales Data Preparation

Module 4: Practical Mathematics and Statistics for AI

• 4.1 Essential Mathematical Concepts
• 4.2 Essential Statistics
• 4.3 Mathematical Reasoning for AI
• 4.4 Case Study: Average Performance Hides a Major Customer Problem
• 4.5 Use Case: Similarity-Based Product Recommendation

Module 5: Machine Learning Fundamentals

• 5.1 Understanding Machine Learning
• 5.2 Supervised Machine Learning
• 5.3 Unsupervised and Other Beginner Methods
• 5.4 Case Study: Customer Churn Prediction
• 5.5 Use Case: Delivery-Time Prediction

Module 6: Model Evaluation and Improvement

• 6.1 Model Evaluation Metrics
• 6.2 Improving Model Performance
• 6.3 Reliable Model Delivery
• 6.4 Case Study: A High-Accuracy Model Misses the Important Cases
• 6.5 Use Case: Spam Email Detection

Module 7: Deep Learning and Computer Vision Basics

• 7.1 Neural Network Fundamentals
• 7.2 Beginner Deep Learning with PyTorch
• 7.3 Computer Vision Foundations
• 7.4 Case Study: Manufacturing Defect Detection with Transfer Learning
• 7.5 Use Case: Product Image Classification

Module 8: Natural Language Processing, Transformers, and LLM Fundamentals

• 8.1 Text Processing Fundamentals
• 8.2 Embeddings and Transformers
• 8.3 Large Language Model Fundamentals
• 8.4 Case Study: Choosing Between a Text Classifier and an LLM for Routing Support Tickets
• 8.5 Use Case: Customer Review Analysis

Module 9: Generative and Multimodal AI Application Development

• 9.1 Prompt Engineering Foundations
• 9.2 Building Controlled Generative AI Applications
• 9.3 Multimodal AI Foundations
• 9.4 Case Study: Invoice Extraction Produces Incorrect Financial Fields
• 9.5 Use Case: Multimodal Product Information Assistant

Module 10: Retrieval-Augmented Generation and Knowledge Assistants

• 10.1 Retrieval Fundamentals
• 10.2 Building a Basic RAG Workflow
• 10.3 RAG Quality and Control
• 10.4 Case Study: A Policy Assistant Returns an Outdated Rule
• 10.5 Use Case: Employee Handbook Assistant

Module 11: Simple AI Agents, APIs, and Deployment

• 11.1 API Development for AI
• 11.2 Basic AI Agents and Tool Use
• 11.3 Beginner Deployment and Operations
• 11.4 Case Study: An Over-Privileged Agent Performs an Unapproved Action
• 11.5 Use Case: IT Support Triage Assistant

Module 12: Responsible AI, Security, Monitoring, and Capstone

• 12.1 Responsible AI Foundations
• 12.2 AI Application Security
• 12.3 Monitoring and Production Readiness
• 12.4 Case Study: Prompt Injection Causes Confidential Data Exposure
• 12.5 Use Case: Beginner AI Release Checklist

Optional Module: AI Agents for Developer

• 1.1 What Are AI Agents?
• 1.2 Significance of AI Agents for Developers
• 1.3 Applications and Trends of AI Agents for Developers
• 1.4 How Does an AI Agent Work?
• 1.5 Core Characteristics of AI Agents
• 1.6 Importance of AI Agents
• 1.7 Types of AI Agents
• 1.8 Comparison Table of AI Agents in Ethics