We introduce a novel type of actor-critic approach for deep reinforcement learning which is based on learning vector quantization. We replace the softmax operator of the policy with a more general and more flexible operator that is similar to the robust soft learning vector quantization algorithm. We compare our approach to the default A3C architecture on three Atari 2600 games and a simplistic...

Vector quantization methods are confronted with a model selection problem, namely the number of prototypical feature representatives to model each class. In this paper we present an incremental learning scheme in the context of figure-ground segmentation. In presence of local adaptive metrics and supervised noisy information we use a parallel evaluation scheme combined with a local utility func...

Man made indoors environments posses regularities which can be efficiently exploited in automated model acquisition by means of visual sensing. In this context we propose an approach for inferring a topological model of an environment from images or the video stream captured by a mobile robot during exploration. The proposed model consists of a set of locations and neighbourhood relationships b...

Two methods to overcome the problems with large vector quantization (VQ) codebooks are lattice VQ (LVQ) and product codes. The approach described in this paper takes advantage of both methods by applying residual VQ with LVQ at all stages. Using LVQ in conjunction with entropy coding is strongly motivated by the fact that entropy constrained but structurally unconstrained VQ design leads to mor...

We propose a new scheme for enlarging generalized learning vector quantization with weighting factors for the several input dimensions which are adapted according to the specific task. This leads to a more powerful classifier with little extra cost as well as the possibility of automatically pruning irrelevant input dimensions. The method is tested on real world satellite image data and compare...

We extend a recent variant of the prototype-based classifier learning vector quantization to a scheme which locally adapts relevance terms during learning. We derive explicit dimensionality-independent large-margin generalization bounds for this classifier and show that the method can be seen as margin maximizer.

This paper presents an unsupervised fuzzy-kernel learning vector quantization algorithm called FKLVQ. FKLVQ is a batch type of clustering learning network by fusing the batch learning, fuzzy membership functions, and kernel-induced distance measures. We compare FKLVQ with the wellknown fuzzy LVQ and the recently proposed fuzzy-soft LVQ on some artificial and real data sets. Experimental results...

We propose to use learning vector quantization (LVQ) in novelty detection where a few outliers exist in training data. The codebook update of original LVQ is modified and the scheme to determine a threshold for each codebook is proposed. Experimental results on artificial and real-world problems are quite promising.