UofU Data Science Courses

Introduction to the Perceptron Algorithm - Lecture 9

Dive into the fundamentals of Perceptron algorithm, exploring its intuitive principles, variations, and practical applications in neural network development.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Machine Learning: Representations and Learning in Online Systems - Lecture 9

Explore how hypothesis representation choices impact online learning algorithms and their effectiveness in machine learning applications.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Transformer Decoder - Pretraining and Finetuning

Master transformer decoder architecture fundamentals, exploring pretraining methods and effective finetuning techniques for advanced natural language processing applications.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Attention and Transformer Encoder Architecture

Master the inner workings of Transformer encoders and attention mechanisms in deep learning, exploring their architecture, self-attention calculations, and practical applications in modern AI.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Mistake Bound Learning and the Halving Algorithm - Lecture 8

Dive into mistake bound learning principles and explore the Halving algorithm's role in machine learning theory and practical applications.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Introduction to Neural Machine Translation and Language Processing

Master the fundamentals of neural machine translation, from embedding matrices and RNNs to advanced concepts like teacher forcing, decoding methods, and BLEU score evaluation metrics.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Linear Classifier Expressiveness in Machine Learning - Lecture 7

Delve into the theoretical foundations of linear classifiers, exploring their expressive capabilities and understanding their role as a fundamental hypothesis class in machine learning.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

How Good is a Learning Algorithm? Quantifying the Learning Process - Lecture 7B

Explore the quantitative aspects of machine learning by examining how many examples are needed to effectively discover and validate hypotheses.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Introduction to Language Modeling: From N-grams to Neural Networks

Explore the evolution of language modeling, from n-grams to neural architectures, covering key concepts like embeddings, transformers, and RLHF implementations.

• YouTube
• 1 hour 20 minutes
• Self-Paced
• Free Video

Decision Trees and Overfitting in Machine Learning - Lecture 6

Dive into advanced concepts of decision trees, focusing on overfitting challenges and practical solutions for building more robust machine learning models.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

Linear Models and Their Geometry in Machine Learning - Lecture 6

Explore the geometry and fundamental concepts of linear classifiers, examining their role as essential tools in machine learning classification problems.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Introduction to Neural Networks: Classification, Softmax, and Training Techniques

Master the fundamentals of neural networks, from nonlinear and multiclass classification to feedforward networks, training techniques, and optimization strategies for improved model performance.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Decision Trees in Machine Learning: Practical Concerns and Overfitting - Lecture 5

Delve into practical aspects of decision tree learning, exploring implementation challenges and understanding how to address overfitting in machine learning models.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Learning Decision Trees Using ID3 Heuristic - Lecture 4

Master the ID3 heuristic algorithm for decision tree learning through practical examples and hands-on application with real datasets, focusing on fundamental concepts and implementation techniques.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Vector Semantics and Word Embeddings in Natural Language Processing

Dive into vector semantics and word embeddings, exploring representation learning, distributional hypothesis, word2vec implementation, and their practical applications in natural language processing.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video