This experimental course is designed as an introduction for software developers aiming to pivot into the field of machine learning engineering. Participants will acquire practical, hands-on knowledge in problem framing, data preparation, model building, and generative AI.
Upon successfully completing the course, participants will have a solid foundation to engage in machine learning-related engineering work and pursue further advanced learning in the field.
Note: Due to the experimental nature of our initial class, the following may be subject to change based on feedback. We will coordinate with students regarding any changes.
Instructor
Denny is a senior engineer at Amazon. He has extensive experience incorporating machine learning features into large-scale products and interviewing engineering candidates for machine learning expertise. He holds both an AWS Machine Learning Associate certificate and an AWS Machine Learning Specialty certificate.
Prerequisites
The class is ideal for software developers who have 1-2 years of working experience. Students should be familiar with Python or any other modern programming language such as Java or C++.
Course Structure and Schedule
-
Duration: We will meet from 6:15 PM to 8:15 PM PST on Fridays for 5 weeks, starting 1/24/2025. Each meeting will cover 2 sessions of the course.
-
Content Delivery
- Live lectures for 10 interactive sessions over 5 evenings via Zoom video conference
- Hands-on exercises: 4 exercises available in Jupyter notebooks
-
Language: English and Mandarin Chinese bilingual
Course Syllabus
We will cover foundational ML knowledge and large language models in this course. Due to the experimental nature of the course, the syllabus may be subject to change based on feedback.
- 8 sessions on AI/ML Fundamentals
- Machine Learning Fundamentals & Workflow
- ML Types and Use Cases
- Complete ML Workflow
- Model Evaluation Basics
- Case Studies
- Data Preprocessing & Feature Engineering
- Data Cleaning Techniques
- Feature Transformation & Creation
- Feature Selection Methods
- Dimensionality Reduction Intro
- Basic Supervised Learning Models
- Linear Regression
- Logistic Regression
- Decision Trees
- Model Evaluation Metrics
- Advanced Supervised Learning Models
- Random Forests
- XGBoost
- Support Vector Machines
- Ensemble Learning Intro
- Neural Network Basics
- Neural Network Architecture
- Backpropagation
- Optimizers & Loss Functions
- PyTorch/TensorFlow Intro
- Time Series Analysis
- Time Series Basic Concepts
- Feature Engineering
- Prediction Models
- Evaluation Methods
- Natural Language Processing Basics
- Text Preprocessing
- Word Embeddings
- Basic Text Classification
- Sentiment Analysis
- MLOps Basics
- Model Deployment
- Version Control
- Monitoring & Maintenance
- Best Practices
- 2 sessions on Generative AI
- Generative AI Basics
- Transformer Architecture
- Large Language Models Overview
- Diffusion Models Intro
- Use Cases
- Prompt Engineering & RAG
- Prompt Engineering Techniques
- RAG Architecture & Applications
- System Integration
- Practical Examples