EDAN95 - Applied Machine Learning

Lund University (LTH) | HT2 2019

This is the repository for the EDAN95 - Tillämpad maskininlärning (Applied Machine Learning) course given at Lunds Tekniska Högskola (LTH) during the Fall 2019 term.

Contents

The following topics are covered in the lab assignments:

• Decision trees
• ID3 algorithm
• Multi-class image classification
• Convolutional Neural Networks (CNN)
• Recurrent Neural Networks (RNN)
• Long-Short Term Memory (LSTM)
• Named Entity Recognition (NER)
• N-grams
• Language models
• Word embeddings
• Naive Bayes Classifier (NBC)
• Nearest Centroid Classifier (NCC)
• Gaussian Naive Bayes Classifier (GNBC)
• Gaussian Mixture Models (GMM)
• Expectation-Maximization algorithm (EM)
• k-Means clustering
• k-Nearest Neighbors (KNN)
• Reinforcement Learning (RL)
• Markov Decision Process (MDP)
• Monte Carlo Methods for On-policy Prediction and Control

Other topics covered in the course lectures and reading material:

• Python and linear algebra fundamentals
• Probability and information theory
• Machine learning fundamentals (linear and logistic regression, perceptron)
• Machine learning concepts (loss, regularisation, evaluation, overfitting)
• Neural network fundamentals (feed forward networks, backpropagation)

Material

Course literature:

• Kevin P. Murphy: Machine Learning, A Probabilistic Perspective. MIT Press, 2012, ISBN: 9780262018029.
• Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning. MIT Press, 2016, ISBN: 9780262035613.
• François Chollet: Deep Learning with Python. Manning, 2018, ISBN: 9781617294433.

Other related literature:

• Aurélien Géron: Hands-On Machine Learning with Scikit-Learn and TensorFlow. Concepts, Tools, and Techniques to Build Intelligent Systems. O'Reilly Media, 2017, ISBN: 9781491962299.
• Tom Mitchell: Machine Learning. McGraw Hill, 1997, ISBN: 0070428077.
• David L. Poole, Alan K. Mackworth: Artificial Intelligence - Foundations of Computational Agents (2e). Cambridge University Press, 2017, ISBN: 9781107195394.
• Richard S. Sutton and Andrew G. Barto: Reinforcement Learning - An Introduction. MIT Press, 2018, ISBN: 9780262039246.

Lectures:

• P. Nugues' slides, available here.
• V. Krueger's slides, available here.
• E.A. Topp's slides are archived and available via web.archive.org.

Other resources

Companion Jupyter notebook and Python code:

• François Chollet: Deep Learning with Python.
• Richard S. Sutton and Andrew G. Barto: Reinforcement Learning - An Introduction (2nd edition).
• Denny Britz: reinforcement-learning.