This paper presents an unsupervised segmentation method for feature sequences based on competitivelearning hidden Markov models. Models associated with the nodes of the Self-Organizing Map learn to become selective to the segments of temporal input sequences. Input sequences may have arbitrary lengths. Segment models emerge then on the map through an unsupervised learning process. The method wa...

We present a framework for constructing representations of space in an autonomous agent which does not obtain any direct information about its location. Instead the algorithm relies exclusively on inputs from its sensors. Activations within a neural network are propagated in time depending on the input from receptors which signal the agent’s own actions. The connections of the network to recept...

The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters.

This paper presents a new training algorithm for Self-structuring Hidden Control Neural (SHC) models, which we presented at ICASSPCl]. The SHC models were trained non-discriminatively for speech recognition applications [2]. Better recognition performance can generally be achieved, if discriminative training is applied in stead. Thus we developed a discriminative training algorithm for SHC mode...

Feedforward neural networks have been successfully developed and applied in many areas because of their universal approximation capability. However, there still remains the problem of determining a suitable network structure for the given task. In this paper, we propose a novel self-organizing neural network which automatically adjusts its structure according to the task. Utilizing both the con...

Change of human systems for the better is often the result of cooperation. Many Systems Intelligent actions have the effect of uncovering the hidden potential for cooperation in a human context. An understanding of the nature and conditions for the emergence of cooperation therefore provides a useful background for the discipline of Systems Intelligence. Forms of cooperation can emerge in repea...

Emotional and self-relevant stimuli are able to automatically attract attention and their use in patients suffering from disorders of consciousness (DOC) might help detecting otherwise hidden signs of cognition. We here recorded EEG in three Locked-in syndrome (LIS) and four Vegetative State/Unresponsive Wakefulness Syndrome (VS/UWS) patients while they listened to the voice of a family member ...