Machine Learning for Software Engineering
Machine Learning for Software Engineering is about learning and optimizing complex tasks that are computationally intractable for exact methods. The goal of this course is to understand the principles of meta-heuristics in optimization as well as key concepts of learning based on neural nets.
News:
- Examplary exam questions >1< >2< >3< >4< >5< >6< ... see >here a digital version<
- Detailed project description >here<
- Download the second public set of optimization Tasks for the project >here<
- Example implementation in C# to get a CSP model from the already parsed XML file, >here<
- Next lecture is canceled!
- Download the first public set of optimization tasks for the project >here< (more to come later)
- Project task will be discussed during the exercise at Monday: 29.05.2017
- First exercise starts with a Python tutorial at Monday, 10th of April.
- Second exercise will be at Monday 24th of April.
- Updated the slides of lecture 2
- The exercises require reading some papers. In order to retrieve them try searching with Google from the university's network.
| Lecture | Topic | Resources |
|---|---|---|
| 04.04.2017 | 1) Introduction to the lecture and optimization Problems | Script |
| 10.04.2017 | Tutorial on Python and Numpy | Notebook |
| 11.04.2017 | 2) Single-State Optimization Techniques | Notebook from lecture |
| 18.04.2017 | 3) Single-State: Simulated Annealing, Tabu Search, and Iterated Local Search; Multi-State Optimization Techniques: Evolutionary Algorithms | |
| 24.04.2017 | Exercise: Implementing Tabu Search and ILS; the Travelling Salesman Problem in Python | |
| 25.04.2017 | 4) Multi-State Optimization Techniques: Genetic Algorithms, Crossover, Line Recombination, Selection Operators | |
| 02.05.2017 | 5) Elitism, Steady-State Algorithm, Memetic Algorithm, Scatter Search, Differential Evolution, Particle Swarm Optimization | |
| 08.05.2017 | Exercise: Application to Software Engineering Problems (read the papers as preparation to the exercise) + Representation of Problems (how to encode?) | Paper1: Optimising Existing Software with Genetic Programming Paper2: Automated Software Transplantation |
| 09.05.2017 | 6) Multi-Objective Optimization | Script |
| 15.05.2017 | Exercise: Application to Software Engineering Problems (read the papers as preparation to the exercise) + Representation of Problems (how to encode?) | Script |
| 16.05.2017 | 7) Combinatorial Optimization Problems (Ant Colony Optimization, Guided Local Search, etc.) | Script |
| 22.05.2017 | No exercise |
|
| 23.05.2017 | 8) Ant Colony Optimization, Constraint Satisfaction Problem |
|
| 29.05.2017 | Exercise: Project Introduction | Script |
| 30.05.2017 | 9) Constraint Satisfaction Problem | |
| 05.06.2017 | No exercise:Whitsun | |
| 06.06.2017 | 10) Canceled! | |
| 12.06.2017 | Exercise: Constraint Satisfaction Problem examples | |
| 13.06.2017 | 11) Dimensionality Reduction: PCA | |
| 19.06.2017 | Exercise: Canceled! | |
| 20.06.2017 | 12) Dimensionality Reduction: PCA continued + Feature Selection | See above |
| 26.06.2017 | Exercise: Tutorial on Keras | Notebook |
| 27.06.2017 | 13) Introduction to Neuronal Networks | |
| 03.07.2017 | Exercise:Tutorial on TensorFlow | Notebook |
| 04.07.2017 | 14) Recap + Architectures of Neuronal Networks | Script |
| 11.07.2017 | 15) Repetition + Summary of the Course |