Deep neural networks have enhanced the performance of decision making systems in many applications, including image understanding, and further gains can be achieved by constructing ensembles. However, designing an ensemble deep is often not very beneficial since time needed to train generally high or gain obtained significant. In this paper, we analyse error correcting output coding (ECOC) fram...

Fingerprint classification is a method of reducing the number candidates needed by fingerprint recognition systems to determine if picture matches one in database. Deep learning has gained lot attraction recent decade including natural language processing, digital image speech recognition, handwritten digit medical assessments, and so on. The subject this paper explore factors affecting using c...

In this paper we present DeepLearningKit an open source framework that supports using pretrained deep learning models (convolutional neural networks) for iOS, OS X and tvOS. DeepLearningKit is developed in Metal in order to utilize the GPU efficiently and Swift for integration with applications, e.g. iOS-based mobile apps on iPhone/iPad, tvOS-based apps for the big screen, or OS X desktop appli...

In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset). This was 0.4% lower than frameworks that used hand-crafted features in addition to the deep convolutional feature extractors. In the present work, we show that combining distributed Gaussian Processes with...

In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network. This allows to trade-off the accuracy of a deep neural network with the computational and memory requirements. This is especially important on a constrained device unable to hold all the weights of the network in memory.

Deep learning refers to a shining branch of machine learning that is based on learning levels of representations. Convolutional Neural Networks (CNN) is one kind of deep neural network. It can study concurrently. In this article, we use convolutional neural network to implement the typical face recognition problem which can overcome the influence of pose or resolution in face recognition. Then,...

One of the most significant graph data analysis tasks is classification, as graphs are complex structures used for illustrating relationships between entity pairs. Graphs essential in many domains, such description chemical molecules, biological networks, social relationships, etc. Real-world complicated and large. As a result, there need to find way represent or encode graph’s structure so tha...

Image understanding using deep convolutional network has reached human-level performance, yet a closely related problem of video understanding especially, action recognition has not reached the requisite level of maturity. We combine multi-kernels based support-vector-machines (SVM) with a multi-stream deep convolutional neural network to achieve close to state-of-the-art performance on a 51-cl...