PhD ceremony: Mr. A.W. Witoelar, 11.00 uur, Academiegebouw, Broerstraat 5, Groningen
Thesis: Statistical physics of learning vector quantization
Promotor(s): prof. M. Biehl, prof. N. Petkov
Faculty: Mathematics and Natural Sciences
The field of machine learning concerns the design of algorithms to learn and recognize complex patterns from data. Learning Vector Quantization (LVQ) constitutes an important family of such algorithms using prototypes which serve as typical examples. Despite its wide range of applications, the theoretical understanding of LVQ in general remains very limited. In this thesis a theoretical framework is constructed using concepts from statistical physics which allows for an exact analysis of the typical learning behaviors of the system. Studies in this thesis compare the characteristics of various LVQ algorithms to demonstrate the robustness of Neural Gas (NG) schemes and the specific advantages of LVQ 2.1 and Robust Soft LVQ algorithms. Furthermore surprising non-trivial behaviors are revealed including learning plateaus and phase transitions in the training process. The results provide insights to general prototype-based learning prescriptions.
On September 20, the University of Oslo in Norway has been officially welcomed as a new Pharmacy Game partner. The Pharmacy Game will become a structural element of their Pharmacy curriculum allowing students to experience the real-world working...
Northern Netherlands Top Dutch Solar Racing team joins forces to prepare for solar race in Morocco.
Not all sugars are the same. Sugar expert Marthe Walvoort is researching how the structure of sugars corresponds to their function in the human body. ‘Even fruit contains unhealthy sugars.’
The UG website uses functional and anonymous analytics cookies. Please answer the question of whether or not you want to accept other cookies (such as tracking cookies).
If no choice is made, only basic cookies will be stored. More information