DAT157 Neural Networks and Advanced Algorithms
Course description for academic year 2017/2018
Contents and structure
The students will get an introduction to Artificial Neural Networks (ANN) and how they may be used in practice to simulate such systems. In the course the simulation tool javANN is used to build rapid prototypes of ANN. In the course one also get an introduction to advanced and well-known algorithms within different fields. Different types of problem solving and recursive thinking will also be given in the lectures. In addition, different aspects of complexity theory with emphasis on the classes P and NP together with approximate solutions based on NP-complete problems.
Content
- In the course one will give a more specific introduction to the biological neuron and different paradigms of ANN
- Fuzzy logics and fuzzy reasoning
- Evolutionary algorithms and simulation of them
- Split and conquer algorithms and dynamic programming
- Approximate algorithms, randomized algorithms kernel based algorithms, heuristic algorithms
- Algorithms for text processing
Learning Outcome
After finished the subject the student should know
Knowledge
- Be able to explain how Artificial Neural Networks and advanced algorithms are working
- Explain how theory of neural Networks and Advanced Algorithms may be used within computer science and engineering
- Explain how neural Networks and Advanced algorithms may be used to solve practical problems of different types
Skills
- Develop applications how to solve problems within different areas
- Design and develop applications how theory for learning and advanced algorithms may be used to build more intelligent applications
- Design effective algorithms for algorithmic problems
General Competence
- Be able to handle complex algorithmic problems, by either design an exact or an approximation algorithm, or making a heuristic solution
- Be able to compare different algorithmic solutions
Entry requirements
Recommended prerequisites: programing in Java or C++ and elementary mathematics. DAT102 Algorithms and data structures
Teaching methods
Lectures and exercises.
Compulsory learning activities
4 compulsory exercises must be completed (within the given deadlines) and approved before the exam can be taken. The exercise can either be written assignments or presentations. Assignments must be submitted in English.
Approved exercises also give access to postponed examination the following semester. However, before a new postponed exam can be taken (the next time the subject is taught), new exercises must be delivered.
Assessment
Oral examination.
Time and place will be announced at Itslearning.
Grading scale is A-F where F is fail.
Examination support material
None.
More about examination support material