While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle pe...
This work presents two kernels which can be applied to sets of spike times. This allows the use of state-of-the-art classification techniques to spike trains. The presented kernels...
Abstract. A convolutional network architecture termed sparse convolutional neural network (SCNN) is proposed and tested on a real-world classification task (car classification). In...
Using the 138,751 patents filed in 2006 under the Patent Cooperation Treaty, coclassification analysis is pursued on the basis of three- and four-digit codes in the International ...
: This paper presents an automatic method and interface to enrich semantically WordNet with categories from general domain classification systems. The method is performed in two co...