Yes, apparently they do. Previous research demonstrated that shallow feed-forward nets sometimes can learn the complex functions previously learned by deep nets while using a similar number of parameters as the deep models they mimic. In this paper we investigate if shallow models can learn to mimic the functions learned by deep convolutional models. We experiment with shallow models and models...

Convolutional deep neural networks (DNN) are state of the art in many engineering problems but have not yet addressed the issue of how to deal with complex spectrograms. Here, we use circular statistics to provide a convenient probabilistic estimate of spectrogram phase in a complex convolutional DNN. In a typical cocktail party source separation scenario, we trained a convolutional DNN to re-s...

Current convolutional neural networks algorithms for video object tracking spend the same amount of computation for each object and video frame. However, it is harder to track an object in some frames than others, due to the varying amount of clutter, scene complexity, amount of motion, and object’s distinctiveness against its background. We propose a depth-adaptive convolutional Siamese networ...

We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a reproducing kernel Hilbert space, the CNN parameters can be represented as a low-rank matrix, which can be relaxed to obtain a convex optimization problem. For lear...

This paper presents an approach to forecast future locations of human hands and objects. Given an image frame, the goal is to predict presence and location of hands and objects in the future frame (e.g., 5 seconds later), even when they are not visible in the current frame. The key idea is that (1) an intermediate representation of a convolutional object recognition model abstracts scene inform...

Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-forward nets sometimes can learn the complex functions previously learned by dee...

Image communication is a significant research area which involves improvement in image coding and communication techniques. In this paper, Principal Component Analysis (PCA) is used for face image coding and the coded images are protected with convolutional codes for transmission over Additive White Gaussian Noise (AWGN) channel. Binary Phase Shift Keying (BPSK) is used for the modulation of di...

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity of different components in the pipeline. We find t...

Vasculature is known to be of key biological significance, especially in the study of cancer. As such, considerable effort has been focused on the automated measurement and analysis of vasculature in medical and pre-clinical images. In tumors in particular, the vascular networks may be extremely irregular and the appearance of the individual vessels may not conform to classical descriptions of ...

Artificial neural networks have been widely used for machine learning tasks such as object recognition. Recent developments have made use of biologically inspired architectures, such as the Convolutional Neural Network. The nature of the Convolutional Neural Network is that each convolutional layer of the network contains a certain number of feature maps or kernels. The number of these used has...