Helge Ritter

Self-organizing semantic maps

Self-organized formation of topographic maps for abstract data, such as words, is demonstrated in this work. The semantic relationships in the data are reflected by their relative distances in the map. Two different simulations, both based on a neural network model that implements the algorithm of the selforganizing feature maps, are given. For both, an essential, new ingredient is the inclusion of the contexts, in which each symbol appears, into the input data. This enables the network to detect the “logical similarity” between words from the statistics of their contexts. In the first demonstration, the context simply consists of a set of attribute values that occur in conjunction with the words. In the second demonstration, the context is defined by the sequences in which the words occur, without consideration of any associated attributes. Simple verbal statements consisting of nouns, verbs, and adverbs have been analyzed in this way. Such phrases or clauses involve some of the abstractions that appear in thinking, namely, the most common categories, into which the words are then automatically grouped in both of our simulations. We also argue that a similar process may be at work in the brain.

Neural computation and self-organizing maps: an introduction

A process for removing sulfur from crude oil by contacting with calcium carbonate-containing material at atmospheric pressures and temperatures less than about 100 DEG F.

BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm

We propose an approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines. In a conservative classification scheme, we found the correct solution after five repetitions. While the classification within the competition is designed for offline analysis, our approach is also well-suited for a real-world online solution: It is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.

Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selection

We analyse a Markovian algorithm for the formation of topologically correct feature maps proposed earlier by Kohonen. The maps from a space of input signals onto an array of formal neurons are generated by a learning scheme driven by a random sequence of input samples. The learning is described by an equivalent Fokker-Planck equation. Convergence to an equilibrium map can be ensured by a criterion for the time dependence of the learning step size. We investigate the stability of the equilibrium map and calculate the fluctuations around it. We also study an instability responsible for a phenomenon termed by Kohonen “automatic selection of feature dimensions”.

Topology-conserving maps for learning visuo-motor-coordination

Abstract We investigate the application of an extension of Kohonens self-organizing mapping algorithm to the learning of visuo-motor-coordination of a simulated robot arm. We show that both arm kinematics and arm dynamics can be learned, if a suitable representation for the map output is used. Due to the topology-conserving property of the map spatially neighboring neurons can learn cooperatively, which greatly improves the robustness and the convergence properties of the algorithm.

On the stationary state of Kohonen's self-organizing sensory mapping

The stationary state of the self-organizing sensory mapping of Kohonen is investigated. For this purpose the equation for the stationary state is derived for the case of one-dimensional and two-dimensional mappings. The equation can be solved for special cases, including the general one-dimensional case, to yield an explicit expression for the local magnification factor of the map.

Three-dimensional neural net for learning visuomotor coordination of a robot arm

An extension of T. Kohonens (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for the visuomotor coordination of a simulated robot arm. Learning occurs by a sequence of trial movements without the need for an external teacher. Using input signals from a pair of cameras, the closed robot arm system is able to reduce its positioning error to about 0.3% of the linear dimensions of its work space. This is achieved by choosing the connectivity of a three-dimensional lattice consisting of the units of the neural net.

An Adaptive P300-Based Online Brain–Computer Interface

The P300 component of an event related potential is widely used in conjunction with brain-computer interfaces (BCIs) to translate the subjects intent by mere thoughts into commands to control artificial devices. A well known application is the spelling of words while selection of the letters is carried out by focusing attention to the target letter. In this paper, we present a P300-based online BCI which reaches very competitive performance in terms of information transfer rates. In addition, we propose an online method that optimizes information transfer rates and/or accuracies. This is achieved by an algorithm which dynamically limits the number of subtrial presentations, according to the subjects current online performance in real-time. We present results of two studies based on 19 different healthy subjects in total who participated in our experiments (seven subjects in the first and 12 subjects in the second one). In the first, study peak information transfer rates up to 92 bits/min with an accuracy of 100% were achieved by one subject with a mean of 32 bits/min at about 80% accuracy. The second experiment employed a dynamic classifier which enables the user to optimize bitrates and/or accuracies by limiting the number of subtrial presentations according to the current online performance of the subject. At the fastest setting, mean information transfer rates could be improved to 50.61 bits/min (i.e., 13.13 symbols/min). The most accurate results with 87.5% accuracy showed a transfer rate of 29.35 bits/min.

Asymptotic level density for a class of vector quantization processes

It is shown that for a class of vector quantization processes, related to neural modeling, that the asymptotic density Q(x ) of the quantization levels in one dimension in terms of the input signal distribution P(x) is a power law Q(x)=C-P(x)(alpha ), where the exponent alpha depends on the number n of neighbors on each side of a unit and is given by alpha=2/3-1/(3n (2)+3[n+1](2)). The asymptotic level density is calculated, and Monte Carlo simulations are presented.

Recognition of human head orientation based on artificial neural networks

Humans easily recognize where another person is looking and often use this information for interspeaker coordination. We present a method based on three neural networks of the local linear map type which enables a computer to identify the head orientation of a user by learning from examples. One network is used for color segmentation, a second for localization of the face, and the third for the final recognition of the head orientation. The system works at a frame rate of one image per second on a common workstation, We analyze the accuracy achieved at different processing steps and discuss the usability of the approach in the context of a visual human-machine interface.