Perception and action are the result of an integration of various sources of information, such as current sensory input, prior experience, or the context in which a stimulus occurs. Often, the interpretation is not trivial hence needs to be learned from the co-occurrence of stimuli. Yet, how do we combine such diverse information to guide our action? Here we use a distance production-reproducti...

In this paper we describe a full-custom register file generator based on a tiling approach to achieve a high density integration. The leaf cells are designed using symbolic layout, providing a high degree of technology independence and portability. Co-simulation and formal proof ensures the validity of the tool.

The paper presents a new technique for extracting symbolic ground facts out of the sensor data stream in autonomous robots for use under hybrid control architectures. The sensor data are used in the form of time series curves of behavior activation values, yielding an image of the environment as perceived through the eyes of useful behaviors. Similar progressions in individual behavior activati...

Imitation plays a very important role in human cognition. Because previous neuroimaging studies on human imitation used rather simple actions as target stimuli, some aspects of imitation such as perceiving target actions or manipulating one's own mental image could not be studied. We used complicated non-symbolic (S-) and symbolic (S+) finger configurations as target stimuli in order to study t...

Classification is one of the data mining problems receiving great attention recently in the database community. This paper presents an approach to discover symbolic classification rules using neural networks. Neural networks have not been thought suited for data mining because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or inte...

Classification is one of the data mining problems receiving great attention recently in the database community. This paper presents an approach to discover symbolic classification rules using neural networks. Neural networks have not been thought suited for data mining because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or inte...