Convolutional neural networks are known to be effective in learning complex image classification tasks. However, how to design the architecture or complexity of the network structure requires a more quantitative analysis of the architecture design. In this paper, we study the effect of model complexity on generalization capability of the convolutional neural networks on large-scale, real-life d...

Convolutional neural networks (CNNs) are biologically-inspired variants of multi-layer perceptrons (MLPs). In biology, a visual cortex contains a complex arrangement of cells. These cells are sensitive to small subregions of the visual field. Inspired by the structure of visual cortices and cells, the notion of receptive fields and local filters are introduced as a core component of convolution...

This paper proposes a new convolutional neural architecture based on treestructures, called the tree-based convolutional neural network (TBCNN). Two variants take advantage of constituency trees and dependency trees, respectively, to model sentences. Compared with traditional “flat” convolutional neural networks (CNNs), TBCNNs explore explicitly sentences’ structural information; compared with ...

Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. We try to apply the conv...

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network. Especially, recurrent neural network and deep convolutional neural network have been applied in ASR successfully. Given the arising problem of training speed, w...

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...

Recently, deep Convolutional Neural Networks have been shown to outperform Deep Neural Networks for acoustic modelling, producing state-of-the-art accuracy in speech recognition tasks. Convolutional models provide increased model robustness through the usage of pooling invariance and weight sharing across spectrum and time. However, training convolutional models is a very computationally expens...