Convolutional neural network (CNN) has a high recognition rate in image and are used embedded systems such as smartphones, robots self-driving cars. Low-end FPGAs candidates for platforms because they achieve real-time performance at low cost. However, CNN significant parameters called weights internal data feature maps, which pose challenge memory capacity. To solve these problems, we exploit ...

Audio source separation is a useful preprocessing step for remixing or transcription of music. It can be shown, that the separation quality increases, if the separation algorithm gets additional side information, e.g. the score of the current mixture [5]. In many cases the score of a musical piece is not available and has to be extracted by a professional musician or an automatic music transcri...

The performance of adaptive filtering can be enhanced by incorporating prior system knowledge. In this paper, we systematically consider regularization strategies exploiting sparseness for the identification of acoustic room impulse responses specifically for multichannel systems. Due to the additional dimensions in the multichannel case, a structured regularization appears to be a natural choi...

In several sensory pathways, input stimuli project to sparsely active downstream populations that have more neurons than incoming axons. Here, we address the computational benefits of expansion and sparseness for clustered inputs, where different clusters represent behaviorally distinct stimuli and intracluster variability represents sensory or neuronal noise. Through analytical calculations an...

This paper shows that the web can be employed to obtain frequencies for bigrams that are unseen in a given corpus. We describe a method for retrieving counts for adjective-noun, noun-noun, and verbobject bigrams from the web by querying a search engine. We evaluate this method by demonstrating that web frequencies and correlate with frequencies obtained from a carefully edited, balanced corpus....

Non-negative tensor factorization (NTF) has recently been proposed as sparse and efficient image representation (Welling and Weber, Patt. Rec. Let., 2001). Until now, sparsity of the tensor factorization has been empirically observed in many cases, but there was no systematic way to control it. In this work, we show that a sparsity measure recently proposed for non-negative matrix factorization...