Abstract
Deep learning has been successfully used in various applications including image classification, natural language processing and game theory. The heart of deep learning is to adopt deep neural networks (deep nets for short) with certain structures to build up the estimator. Depth and structure of deep nets are two crucial factors in promoting the development of deep learning. In this paper, we propose a novel tree structure to equip deep nets to compensate the capacity drawback of deep fully connected neural networks (DFCN) and enhance the approximation ability of deep convolutional neural networks (DCNN). Based on an empirical risk minimization algorithm, we derive fast learning rates for deep nets.
Highlights
Deep learning [1], a learning strategy based on deep neural networks, has recently made significant breakthrough on bottlenecks of classical learning schemes, such as support vector machines, random forests and boosting algorithms, by demonstrating its remarkable success in such research areas as computer vision [2], speech recognition [3], and game theory [4]
The necessity of depth has been rigorously verified from the viewpoints of approximation theory and representation theory, via showing the advantages of deep nets in localized approximation [6], sparse approximation in the frequency domain [7, 8], sparse approximation in the spatial domain [9], manifold learning [10, 11], hierarchical structures grasping [12, 13], piecewise smoothness realization [14], universality with bounded number of parameters [15, 16] and rotation invariance protection [17]
We propose an appropriate structure to equip deep nets with a combination of some smaller variance provided by deep convolutional neural networks (DCNN) and a corresponding less bias advantage of deep fully connected neural networks (DFCN)
Summary
Deep learning [1], a learning strategy based on deep neural networks (deep nets), has recently made significant breakthrough on bottlenecks of classical learning schemes, such as support vector machines, random forests and boosting algorithms, by demonstrating its remarkable success in such research areas as computer vision [2], speech recognition [3], and game theory [4]. In designing learning algorithms, and may result in large variance Equipping deep nets with an appropriate structure to reduce the number of parameters of DFCN while enhancing the approximation ability of DCNN requires some desirable balance of the bias and variance in the learning process. Deep nets with tree structures, revealed by our study, possess three theoretical advantages, namely: the capacity, as measured by the covering number, is much smaller than that of DFCN; based on tree structures, the approximation capability is comparable with that of DFCN; and fast learning rate is achieved, by applying an empirical risk minimization algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
