Due to the recent breakthroughs achieved by Convolutional Neural Networks (CNNs) for various computer vision tasks (He et al., 2015; Taigman et al., 2014; Karpathy et al., 2014), CNNs are highly regarded technology for inclusion into real-life vision applications. However, CNNs have a high risk of failing due to adversarial examples, which fool them consistently with the addition of small pertu...

Convolutional Neural Networks (CNNs) have been successfully used for many computer vision applications. It would be beneficial to these applications if the computational workload of CNNs could be reduced. In this work we analyze the linear algebraic properties of CNNs and propose an algorithmic modification to reduce their computational workload. An up to a 47% reduction can be achieved without...

In this paper, we study the relationship between the standard cellular neural network (CNN) and the resonant tunneling diode (RTD)-based CNN. We investigate the functional and advanced capabilities of a new generation of CNNs that exploit the multiplicity of steady states. We also include in the analysis higher order CNNs. Furthermore, some methods for designing RTD-based CNNs with multiple ste...

In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e.g., such base deep CNNs are trained to recognize different subsets of tens of thousands of atomic object classes. First, a two-layer (category layer and object class layer) ontology is constructed to achiev...

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving many state-of-the-art (SOA) visual processing tasks. Even though Graphical Processing Units (GPUs) are most often used in training and deploying CNNs, their power consumption becomes a problem for real time mobile applications. We propose a flexible and efficient CNN accelerator architecture wh...

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank ten...

We propose a method to compare the visual primitives used by radiologists and convolutional neural networks (CNNs) for the identification of diseased tissue in mammograms. Using the latest advances in neural network interpretability, we investigate the visual primitives used by two different CNNs, a baseline model and our own high-performance model, to perform automatic medical diagnosis. By vi...

Recently, Deep Learning, especially through Convolutional Neural Networks (CNNs) has been widely used to enable the extraction of highly representative features. This is done among the network layers by filtering, selecting, and using these features in the last fully connected layers for pattern classification. However, CNN training for automated endoscopic image classification still provides a...

Convolutional neural networks (CNNs) have yielded the excellent performance in a variety of computer vision tasks, where CNNs typically adopt a similar structure consisting of convolution layers, pooling layers and fully connected layers. In this paper, we propose to apply a novel method, namely Hybrid Orthogonal Projection and Estimation (HOPE), to CNNs in order to introduce orthogonality into...

The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a ...