|
Curriculum Artificial Intelligence
Obligatory Courses AI
AI courses
For the AI courses
** in the curriculum, a student can take any track course (see track descriptions below). In addition, one course from the following list can be chosen:
|
|
|
| *: Restricted to one course from this list as a constrained choice course, in all other cases as a free choice course. **: For free choice courses, you are allowed to select 12 EC from the list. |
Track Gaming
The
track Gaming takes two academic years (120 EC), which awards a Master of Science degree in Artificial Intelligence.
The track Gaming provides students expertise in the field of game-oriented systems. Students will learn methods and techniques for the design and implementation of intelligent multimedia systems such as games (console, Internet or platform-specific) and general game-oriented systems. This programme provides knowledge on game programming, learning in games, and multimedia analysis. Human-computer interaction and visualization techniques are covered in the field of image processing, computer vision, virtual reality and multimedia. The emphasis of this programme is on learning and intelligent techniques for gaming such as machine learning and pattern recognition, automated learning, and multimedia understanding. The gaming programme consists of the following parts:
- AI-techniques
- Human-computer interaction
- Programming
- 3-D Graphics/visualization
- Games and multi-agents
- Intelligent systems (e.g. robots)
- Design and implementation of game-oriented systems.
Track Intelligent Systems
This programme is focused on intelligent methods and techniques for (autonomous) systems that interpret sensory information of different modalities and use that information to generate intelligent and goal-directed behavior. Intelligent methods and techniques are of vital importance of any intelligent autonomous system, which perceives and acts. This includes the formalization, generalization and learning of goal-directed behavior in autonomous systems such as autonomous vehicles, robots, or visual servoing systems. Further, this program focuses on methodologies to create intelligent multimedia-information systems to access and classify multimodal information such as the retrieval/search of documents/images/videos, data mining, and intelligent agents on the Internet. Main topics are:
- machine learning and computer vision
- robots and autonomous systems
- design of multi-agent systems
- design of organisation of autonomous systems.
Track Learning Systems
Learning Systems are systems that use experience to construct a general model and to improve their performance. Learning methods are used in a variety of systems including systems for data mining, text and image classification, recognition of objects and information in texts, data mining, robot control. Emphasis in this track is on algorithms, models for learning, theories that explain why algorithms work, multi-agent reinforcement learning and transfer learning for multiple modalities. The track is associated with the Autonomous Intelligent Systems group and the Adaptive Information Management group but freely collaborates with others.
Track Natural Language Processing and Learning
Over the past few years, research towards natural language processing has shown strong evidence as to the effectiveness of models that involve both hierarchical structure as well as statistical learning from corpora.
This track studies the state-of-the-art statistical models for complex language processing tasks such as parsing, language modeling and machine translation. A characteristic of some of these models is that they involve defining probability measures over hierarchical structure, e.g., trees and graphs. The track covers supervised as well as unsupervised methods for learning these models directly from large training corpora and provides the necessary background for research in Computational Linguistics and Natural Language Processing.
|
| Track coordinator Natural Language Processing and Learning
|
| dr. K. Sima'an
|
K.Simaan@uva.nl
|
|
|
Track Web Information Processing
The Internet has become an integral part of our society and economy over the last two decades. The way we access, provide, and exchange information as changed dramatically with the rise of the Internet. Students will learn methods and techniques for the design, implementation, and use of information processing technology in the context of a variety of Internet applications, ranging from search engines to text analysis.
Web Information Processing has developed from a number of research areas, including Computer Science, Library Science, Artificial Intelligence, Data Mining, and Natural Language Processing. While Web Information Processing builds on techniques from a variety of research areas, there a number of research problems that are specific to the Web applications, such as the design of Internet search engines, efficient linking of related information across the Web, improving information extraction from social networking sites, and the access of foreign language information. In addition, the sheer scale of the Internet opens up tremendous opportunities for data mining approaches, while at the same time posing interesting research challenges with respect to robustness and scalability. Within the Web Information Processing track students will be familiarized with several data mining, natural language processing, and link-based techniques that are not only relevant to this track but also for many other Artificial Intelligence applications.
As the Internet is rapidly developing, so is the research covered in the Web Information Processing track. This track does not only cover the well-established techniques within the area but is also very much forward-looking, discussing the science behind cutting-edge technologies and anticipating Web technologies that yet have to be fully realized. This will enable students to participate in and help drive future developments of Web information technologies in a commercial or academic environment.
Main topics are:
- Big data
- Intelligent crawling
- Unsupervised content extraction
- Information retrieval
- Web 2.0 and social media analysis
- Large scale text mining
- Web 3.0 and information extraction
- Machine translation
- Link analysis
- Opinion extraction and analysis
|
| Track coordinator Web Information Processing
|
| dr. M. de Rijke
|
M.deRijke@uva.nl
|
|
|
|
| Obligatory Courses and Project WIP
|
EC
|
semester
|
block
|
| Advanced Information Retrieval (6 EC)
|
6
|
2
|
1
|
| Web Text Mining (6 EC)
|
6
|
1
|
1
|
| Profile Project AI-WIP (6 EC)
|
6
|
2
|
3
|
|
|
Transitional Provisions
Transitional Provisions for students who started in 2011-2012 or earlier:
|
| Old course
|
Replacement in 2012-2013
|
Remarks
|
| Multi-Agent Systems (3 EC)
|
Autonomous Agents (6 EC)
|
Students that did not pass Multi-Agent Systems in 2011-2012 or earlier will do half of Autonomous Agents for 3 EC
|
| Autonomous Agents and Multi-Agent Systems (6 EC)
|
Advanced Topics in Autonomous Agents (6 EC)
|
|
| Knowledge Representation (3 EC)
|
Students that did not pass Knowledge Representation 3 EC in 2011-2012 or earlier will be offered the opportunity to do an extra resit in 2012-2013
|
Students that do not pass the resit will be offered an alternative of 3 EC in consultation with the Programme Director
|
|
|
|