This paper develops fundamental limits of deep neural network learning by characterizing what is possible if no constraints are imposed on the algorithm and amount training data. Concretely, we consider Kolmogorov-optimal approximation through networks with guiding theme being a relation between complexity function (class) to be approximated approximating in terms connectivity memory requiremen...

In recent years, deep neural network exhibits its powerful superiority on information discrimination in many computer vision applications. However, the capacity of deep neural network architecture is still a mystery to the researchers. Intuitively, larger capacity of neural network can always deposit more information to improve the discrimination ability of the model. But, the learnable paramet...

Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architect...

—Deep neural networks are state-of-the-art models for understanding the content of images, video and raw input data. However, implementing a deep neural network in embedded systems is a challenging task, because a typical deep neural network, such as a Deep Belief Network using 128×128 images as input, could exhaust Giga bytes of memory and result in bandwidth and computing bottleneck. To addre...

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...

We propose a novel deep neural network architecture for speech recognition that explicitly employs knowledge of the background environmental noise within a deep neural network acoustic model. A deep neural network is used to predict the acoustic environment in which the system in being used. The discriminative embedding generated at the bottleneck layer of this network is then concatenated with...

We propose in this work the gradient-enhanced deep neural network (DNN) approach for function approximations and uncertainty quantification. More precisely, proposed adopts both evaluations associated gradient information to yield enhanced approximation accuracy. In particular, is included as a regularization term DNN approach, which we present posterior estimates (by two-layer networks) simila...

Image classification and retrieval systems have gained more attention because of easier access to high-tech medical imaging. However, the lack of availability of large-scaled balanced labelled data in medicine is still a challenge. Simplicity, practicality, efficiency, and effectiveness are the main targets in medical domain. To achieve these goals, Radon transformation, which is a well-known t...