A Review of Deep Learning Research

Abstract

With the advent of big data, deep learning technology has become an important research direction in the field of machine learning, which has been widely applied in the image processing, natural language processing, speech recognition and online advertising and so on. This paper introduces deep learning techniques from various aspects, including common models of deep learning and their optimization methods, commonly used open source frameworks, existing problems and future research directions. Firstly, we introduce the applications of deep learning; Secondly, we introduce several common models of deep learning and optimization methods; Thirdly, we describe several common frameworks and platforms of deep learning; Finally, we introduce the latest acceleration technology of deep learning and highlight the future work of deep learning.

Deep Learning-Based Indoor Distance Estimation Scheme Using FMCW Radar

“…If the distance to the target is R, the signal that is reflected after hitting the target has travelled over the distance of 2R, which is twice the distance R. These are summarized in terms of distance and time, as shown in Equations (1) and (2), respectively. The calculation formula is expressed as follows [11][12][13][14][15]:…”

“…Meanwhile, the deep learning method is considered to overcome these limitations [13]. By applying the deep learning technology to the received data from FMCW Radar, it can be classified in terms of different distance to the target even with noise and clutter, because the received data have different patterns at different distances.…”

Deep Learning-Based Bootstrap Detection Scheme for Digital Broadcasting System

“…Deep Learning have shown great performance in various fields such as pattern recognition [22], [23]. In this aspect, this paper deal with convolutional neural network (CNN) among deep learning technologies for detection of bootstrap signal.…”

The Impact of Transforming Unstructured Data into Structured Data on a Churn Prediction Model for Loan Customers

“…When the sigmoid activation function is used, the "vanishing gradient problem" can occur, which means that the gradient becomes vanishingly small with recurrent multiplication to compute the gradients of the other layers as the sigmoid function has gradients in the range of 0 to 1. The CNN model consisted of a convolution layer, max pooling layer, and fully connected layer [50]. The size of the CNN filter was 2×128, 3×128, 4×128, and 5×128 in the convolution layer of this study, which means that the filters identify the characteristics of two consecutive letters, three consecutive letters, four consecutive letters, and five consecutive letters, respectively.…”