Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic template matching. In this framework, we give the geometric structures of di...

Deep networks can potentially express a learning problem more efficiently than local learning machines. While deep networks outperform local learning machines on some problems, it is still unclear how their nice representation emerges from their complex structure. We present an analysis based on Gaussian kernels that measures how the representation of the learning problem evolves layer after la...

Hashing has been widely used for large-scale search due to its low storage cost and fast query speed. By using supervised information, supervised hashing can significantly outperform unsupervised hashing. Recently, discrete supervised hashing and deep hashing are two representative progresses in supervised hashing. On one hand, hashing is essentially a discrete optimization problem. Hence, util...

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch learning setting, which requires the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios where new data arrives sequentially in a stream form. We aim to address an open challenge of “Online Deep Learning” (ODL) for learning DNNs on the fly in an on...

Efficient resource scheduling is essential for maximal utilization of expensive deep learning (DL) clusters. Existing cluster schedulers either are agnostic to machine (ML) workload characteristics, or use heuristics based on operators' understanding particular ML framework and workload, which less efficient not general enough. In this article, we show that DL techniques can be adopted design a...

This paper considers security risks buried in the data processing pipeline in common deep learning applications. Deep learning models usually assume a fixed scale for their training and input data. To allow deep learning applications to handle a wide range of input data, popular frameworks, such as Caffe, TensorFlow, and Torch, all provide data scaling functions to resize input to the dimension...

Improving return forecasting is very important for both investors and researchers in financial markets. In this study we try to aim this object by two new methods. First, instead of using traditional variable, gold prices have been used as predictor and compare the results with Goyal's variables. Second, unlike previous researches new machine learning algorithm called Deep learning (DP) has bee...

Deep learning algorithms seek to exploit the unknown structure in the input distribution in order to discover good representations, often at multiple levels, with higher-level learned features defined in terms of lower-level features. The objective is to make these higherlevel representations more abstract, with their individual features more invariant to most of the variations that are typical...

In this paper, I will introduce to the APSIPA audience an emerging area of machine learning, deep-structured learning. It refers to a class of machine learning techniques, developed mostly since 2006, where many layers of information processing stages in hierarchical architectures are exploited for pattern classification and for unsupervised feature learning. First, the brief history of deep le...