Python Fundamentals

ML1: Introduction to Machine Learning

ML2: Advanced Machine Learning

Machine Learning Topics

Python Fundamentals

Master the essential Python programming concepts and tools needed for machine learning. This course covers data structures, functions, libraries, and best practices for ML development.

1. Python Basics

Variables, data types, control flow, and functions.

2. Data Structures

Lists, dictionaries, sets, and their applications in ML.

3. NumPy Essentials

Array operations, broadcasting, and numerical computing.

4. Data Processing with Python

File I/O, data cleaning, and preprocessing techniques.

Python Fundamentals

Essential Python concepts and tools for machine learning development.

Introduction to Machine Learning

Start your journey into machine learning with fundamental concepts, mathematical foundations, and practical implementations. This course provides a solid foundation for understanding modern ML techniques.

1. Introduction to ML Fundamentals

Core concepts, terminology, and the ML pipeline.

2. Linear Regression

Understanding and implementing basic regression models.

3. Model Evaluation and Validation

Statistical validation, cross-validation techniques, and performance metrics.

4. Matrix Structures in Machine Learning

Understanding different matrix structures and their applications in ML.

5. Regression Methods: From Linear to Logistic

Exploring regression methods, from linear regression solutions to logistic regression and optimization.

6. Decision Trees and Random Forests

Understanding tree-based methods, from basic decision trees to ensemble techniques.

7. Nearest Neighbors and Naive Bayes

Exploring instance-based learning and probabilistic classification methods.

10. Matrix Factorization and Collaborative Filtering

Deep dive into SVD and its applications in recommendation systems.

12. Dimensional Transformations: From SVMs to Deep Learning

Understanding how different ML approaches transform data into higher dimensions.

13. Introduction to Neural Networks for ML Practitioners

Bridging traditional ML approaches with neural networks and modern frameworks.

14. Understanding Bias in Deep Learning Systems

Examining bias introduction, detection, and mitigation in deep learning systems.

Advanced Machine Learning

Dive deep into advanced ML concepts, neural architectures, and state-of-the-art techniques. This course builds on ML1 to explore cutting-edge applications, with a special focus on Large Language Models and modern architectures.

1. Introduction to Deep Learning

History, evolution, neural network concepts, and framework comparisons.

2. Neural Networks & Backpropagation

Detailed backpropagation, gradient descent variations, and training challenges.

3. Building a Real-World Housing Price Predictor

Practical implementation of neural networks for housing price prediction using the California Housing Dataset.

4. Vector Representations & Similarity Measures

Explore vector representations and similarity measures through practical examples, including food preference vectors, sparse representation challenges, and learned representations.

5. Autoencoders & Embeddings

Autoencoder architectures, embedding spaces, and dimensionality reduction.

6. From Autoencoders to Embeddings

Explore the evolution from autoencoders to modern embedding techniques, focusing on Word2Vec, GloVe, and practical applications in recommendation systems.

7. Sequence Models & Attention

Understanding sequence models, attention mechanisms, and their applications.

8. Convolutional Neural Networks

Deep dive into CNNs, their architectures, and applications.

9. From Supervised to Generative Learning

Exploring the transition from supervised learning to generative models.

10. Introduction to Large Language Models

Understanding the fundamentals of LLMs and their capabilities.

11. Practical LLM Integration & API Development

Learn to integrate and develop with LLM APIs effectively.

12. Retrieval Augmented Generation (RAG)

Deep dive into RAG architecture and implementation.

13. Evaluating LLMs - Metrics and Methods

Learn comprehensive approaches to evaluating LLM performance.

14. LLMs as Decision Makers and Agents

Explore how LLMs can be used for decision-making and autonomous tasks.

15. Future Trends in LLMs

Looking ahead at emerging developments in LLM technology.

Special Topics in Machine Learning

Explore specialized topics and cutting-edge developments in machine learning, featuring guest lectures and focused deep dives into specific areas of ML.

1. AI Suite

A co-developed libary with Andrew Ng, that allows for rapid swaping of LLM providers.

2. Ranking Systems

Explore different approaches to ranking and evaluation, from traditional methods to modern ML-based systems.

3. SVD: Theory & Applications

Deep dive into Singular Value Decomposition, its mathematical foundations, and applications in machine learning.

4. Reinforcement Learning

Explore the fundamentals and advanced concepts of reinforcement learning, from Q-learning to deep RL architectures.

5. Principal Component Analysis (PCA)

A comprehensive exploration of PCA, from intuitive understanding to mathematical foundations and practical applications.

6. Markov Processes

Deep dive into Markov chains, Hidden Markov Models, and their applications in machine learning and sequential data analysis.

7. Transfer Learning

Leveraging pre-trained models for new tasks and domains, with practical implementations and best practices.

8. Retrieval Augmented Generation

Enhancing LLMs with external knowledge retrieval, focusing on architecture, implementation, and best practices.

9. Probabilistic Programming

Explore probabilistic programming frameworks, Bayesian inference, and MCMC methods for modern machine learning.

10. Applied Examples

Hands-on examples using real-world datasets, featuring detailed notebooks with data analysis, model development, and evaluation techniques.

11. Logistic Regression

Deep dive into logistic regression, covering theory, implementation, and practical applications in classification tasks.