Results 1 
4 of
4
Competitive Learning Algorithms for Robust Vector Quantization
, 1998
"... The efficient representation and encoding of signals with limited resources, e.g., finite storage capacity and restricted transmission bandwidth, is a fundamental problem in technical as well as biological information processing systems. Typically, under realistic circumstances, the encoding and com ..."
Abstract

Cited by 24 (1 self)
 Add to MetaCart
(Show Context)
The efficient representation and encoding of signals with limited resources, e.g., finite storage capacity and restricted transmission bandwidth, is a fundamental problem in technical as well as biological information processing systems. Typically, under realistic circumstances, the encoding and communication of messages has to deal with different sources of noise and disturbances. In this paper, we propose a unifying approach to data compression by robust vector quantization, which explicitly deals with channel noise, bandwidth limitations, and random elimination of prototypes. The resulting algorithm is able to limit the detrimental effect of noise in a very general communication scenario. In addition, the presented model allows us to derive a novel competitive neural networks algorithm, which covers topology preserving feature maps, the socalled neuralgas algorithm, and the maximum entropy softmax rule as special cases. Furthermore, continuation methods based on these noise models impr...
Unsupervised OnLine Data Reduction for Memorisation and Learning in Mobile Robotics
, 2003
"... THE AMOUNT OF DATA AVAILABLE to a mobile robot controller is staggering. This thesis investigates how extensive continuousvalued data streams of noisy sensor and actuator activations can be stored, recalled, and processed by robots equipped with only limited memory buffers. We address three robot m ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
THE AMOUNT OF DATA AVAILABLE to a mobile robot controller is staggering. This thesis investigates how extensive continuousvalued data streams of noisy sensor and actuator activations can be stored, recalled, and processed by robots equipped with only limited memory buffers. We address three robot memorisation problems, namely Route Learning (store a route), Novelty Detection (detect changes along a route) and the Lost Robot Problem (find best match along a route or routes). A robot learning problem called the RoadSign Problem is also addressed. It involves a longterm delayed response task where temporal credit assignment is needed. The limited memory buffer entails that there is a tradeoff between memorisation and learning. A traditional overall data compression could be used for memorisation, but the compressed representations are not always suitable for subsequent learning. We present a novel unsupervised online data reduction technique which focuses on change detection rather than overall data compression. It produces reduced sensory flows which are suitable for storage in the memory buffer while preserving underrepresented inputs. Such inputs can be essential when using temporal credit assignment for learning a task. The usefulness of the technique is evaluated through a number of experiments on the identified robot problems. Results show that a learning ability can be introduced while at the same time maintaining memorisation capabilities. The essentially symbolic representation, resulting from the unsupervised online reduction could in the extension also help bridge the gap between the raw sensory flows and the symbolic structures useful in prediction and communication.
Deterministic Annealing for Topographic Vector Quantization and SelfOrganizing Maps
 Proceedings of the Workshop on SelfOrganising Maps, volume 7 of Proceedings in Artificial Intelligence
, 1997
"... We have developed a robust optimization scheme for selforganizing maps in the framework of noisy vector quantization. Based on a cost function that takes distortions from channel noise into account we derive a fuzzy algorithm of EMtype for topographic vector quantization (STVQ) which employs deter ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
We have developed a robust optimization scheme for selforganizing maps in the framework of noisy vector quantization. Based on a cost function that takes distortions from channel noise into account we derive a fuzzy algorithm of EMtype for topographic vector quantization (STVQ) which employs deterministic annealing. This annealing process leads to phase transitions in the cluster representation for which we are able to calculate critical modes and temperatures as a function of the neighbourhood function and the covariance matrix of the data. Similar results are obtained for the automatic selection of feature dimensions. Deterministic annealing also offers an alternative to the heuristic stepwise shrinking of the neighbourhood width in the SOM and makes it possible to use the neighbourhood solely to encode desired neighbourhood relations between the clusters. A soft version of the SOM (SSOM) is derived as a computationally efficient approximation to the Estep of STVQ. Both methods ar...
Phase Transitions in Soft Topographic Vector Quantization
 Artificial Neural Networks ICANN'97
, 1997
"... . We have developed an algorithm (STVQ) for the optimization of neighborhood preserving maps by applying deterministic annealing to an energy function for topographic vector quantization. The combinatorial optimization problem is solved by introducing temperature dependent fuzzy assignments of data ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
. We have developed an algorithm (STVQ) for the optimization of neighborhood preserving maps by applying deterministic annealing to an energy function for topographic vector quantization. The combinatorial optimization problem is solved by introducing temperature dependent fuzzy assignments of data points to cluster centers and applying an EMtype algorithm at each temperature while annealing. The annealing process exhibits phase transitions in the cluster representation for which we calculate critical modes and temperatures expressed in terms of the neighborhood function and the covariance matrix of the data. In particular, phase transitions corresponding to the automatic selection of feature dimensions are explored analytically and numerically for finite temperatures. Results are related to those obtained earlier for Kohonen's SOMalgorithm which can be derived as an approximation to STVQ. The deterministic annealing approach makes it possible to use the neighborhood function solely ...