Course Outline and Administrative Issues

Bayesian Machine Learning and Information Processing (5SSD0)

Logistic Issues

  • When: 3rd quartile, at $8$ weeks of $4$ hours per week.

  • Load: Total workload is 5 ECTS $\Rightarrow 5\times 28 \text{[hrs/ECTS]} = 140$ hours or $140/32 \approx 4.4$ study hours per lecture.

  • Web

  • Instructors

Why Take This Class?

  • Suppose you need to develop an algorithm for a complex DSP task, e.g., a speech recognition engine. This is what you'll do:

    1. Choose a set of candidate algorithms $y=H_k(x;\theta)$ where $k \in \{1,2,\ldots,K\}$ and $\theta \in \Theta_k$; (you think that) there's an algorithm $H_{k^*}(x;\theta^*)$ that performs according to your liking.
    2. You collect a set of examples $D=\{(x_1,y_1),(x_2,y_2),\ldots,(x_N,y_N)\}$ that are consistent with the correct algorithm behavior.
  • Using the methods from this class, you will be able to design a suitable algorithm through learning from the data set, thus achieving:
    1. model selection, i.e., find $k^*$
    2. parameter estimation, i.e., find $\theta^*$
  • Better yet, we will discuss methods that find distributions $p(k|D)$ and $p(\theta|D)$ that represent your knowledge about the best models and parameters, given the data set.

Materials

  • Book (free download link):

  • Mostly used for background reading as the (mandatory) slides are the main resource.

  • Book theme: Whatever you do in machine learning, you can do it better with Bayesian methods.
  • Contains much more material; great for future study and reference.

Exam Guide

  • Tested material consists of these lecture notes, reading assignments (as assigned in the first cell/slide of each lecture notebook) and exercises (see class website).
  • Advice: Make Exercises, (to be) posted and regularly updated on the course website.
  • You are not allowed to use books nor bring printed or handwritten formula sheets to the exam. Difficult-to-remember formulas are supplied at the exam sheet (see old exams).
  • You may use a simple pocket calculator, but no smartphones (only arithmetic assistance is allowed.)

OPTIONAL SLIDES

  • Slides that are not required for the exam are preceded by an "OPTIONAL SLIDES" header.
In [1]:
open("../../styles/aipstyle.html") do f
    display("text/html", read(f,String))
end
In [ ]: