header

Machine Learning


Semester:

WS 2019

Type:

Lecture

Lecturer:

Credits:

V3 + Ü1 (6 ECTS credits)

Lecture Description

The goal of Machine Learning is to develop techniques that enable a machine to "learn" how to perform certain tasks from experience.

The important part here is the learning from experience. That is, we do not try to encode the knowledge ourselves, but the machine should learn it itself from training data. The tools for this are statistical learning and probabilistic inference techniques. Such techniques are used in many real-world applications. This lecture will teach the fundamental machine learning know-how that underlies such capabilities. In addition, we show current research developments and how they are applied to solve real-world tasks.

Example questions that could be addressed with the techniques from the lecture include

  • Is this email important or spam?
  • What is the likelihood that this credit card transaction is fraudulent?
  • Does this image contain a face?

Exercises

The class is accompanied by exercises that will allow you to collect hands-on experience with the algorithms introduced in the lecture.

There will be both pen&paper exercises and practical programming exercises (roughly 1 exercise sheet every 2 weeks). Please submit your solutions electronically through the RWTH Moodle system.

We ask you to work in teams of 2-3 students.

Literature

The first half of the lecture will follow the book by Bishop. For the second half, we will use the Deep Learning book by Goodfellow as a reference.

  • Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep learning, MIT Press, 2016

Wherever research papers are necessary for a deeper understanding, we will make them available in RWTH Moodle.

Additional Resources

  • Kevin Murphy, Machine Learning -- A Probabilistic Perspective, MIT Press, 2012.

Python Resources

Course Schedule
Date Title Content Material
Introduction Introduction, Probability Theory, Bayes Decision Theory, Minimizing Expected Loss
Prob. Density Estimation I Parametric Methods, Gaussian Distribution, Maximum Likelihood
Prob. Density Estimation II Nonparametric Methods, Histograms, Kernel Density Estimation
Probability Density Estimation III Mixture of Gaussians, k-Means, Clustering, EM-Clustering, EM-algorithm
Linear Discriminants I Linear Discriminant Functions, Least squares Classification, Generalised Linear Models
Exercise 1 Python Tutorial, Probability Density, GMM, EM
Linear Discriminants II Logistic Regression, Iteratively Reweighted Least-Squares, Softmax Regression, Error Function Analysis
Linear Discriminants III Softmax Regression
SVMs I Support Vector Machines
SVMs II Non-linear SVMs
Adaboost Model Combination, AdaBoost, Exponential error, Sequential Additive Minimization
Neural Networks I Single-Layer Perceptron, Multi-Layer Perceptron, Mapping to Linear Discriminants, Error Functions, Regularization, Multi-layer Networks, Chain rule, Gradient Descent
Exercise 2 Linear Discriminants, SVM
Neural Networks II Backpropagation, Computational Graphs, Stochastic Gradient Descent, Minibatch Learning, Optimizers (Momentum, RMS-Prop, AdaGrad, Adam)
Optimisation Optimizers (Momentum, RMS-Prop, AdaGrad, Adam), Tricks of the Trade
Exercise 3 AdaBoost
Convolutional Neural Networks I CNNs, Convolutional Layers, Pooling Layers, LeNet
Exercise 4 Softmax, Backpropogation
Tutorial Tensorflow
Convolutional Neural Networks II ImageNet Challenge, Notable Architectures, AlexNet, VGGNet, Inception, Visualizing CNNs
CNN Architectires and Applications Residual Networks, Visualising CNNs, Applications of CNNs
Word Embeddings Dealing with Discrete Data, Word Embeddings, word2vec, GloVe, Hierarchical Softmax, Motivation for Recurrent Networks
Recurrent Neural Networks I Plain RNNs, Backpropagation through Time, Practical Issues, Initialization
Recurrent Neural Networks II LSTM, GRU, Applications of RNNs
Exercise 5 CNNs
Disclaimer Home Visual Computing institute RWTH Aachen University