Computational Methods for Deep Learning
Theory, Algorithms, and Implementations
Article
Multi-exposure image fusion (MEF) is a convenient way to get high dynamic range (HDR) images. However, when the input sequence with a large difference in exposure time, the existing MEF algorithms cannot well ...
Article
In this work, we put forward a concept of Besicovitch almost anti-periodic functions on time scales, which is new even when time scale $$\math...
Chapter and Conference Paper
This article is devoted to the problem of dynamic output-feedback control for a class of discrete-time multirate systems under the scheduling of the Round-Robin (R-R) communication protocol. In order to reflec...
Article
The lack of flexibility and safety in C language development has been criticized for a long time, causing detriments to the development cycle and software quality in the embedded systems domain. TypeScript, as...
Article
Pattern classification has always been essential in computer vision. Transformer paradigm having attention mechanism with global receptive field in computer vision improves the efficiency and effectiveness of ...
Article
Gait-based pedestrian identification has important applications in intelligent surveillance. From anatomical viewpoint, the physical uniqueness of human gait is physiological discriminative of individuals. The...
Chapter
In this chapter, we start from transfer learning and introduce the relationship between learners. We use ensemble learning to combine them together and hope to get a strong learner from a weak learner by chang...
Chapter
There are a plethora of deep learning platforms available at present. The famous one is MATLAB deep learning toolbox developed by MathWorks which simplifies deep learning computations and reduces the workload ...
Chapter
In this chapter, we will emphasize computational iterations in GANs (i.e., generative adversarial networks) [46] and Siamese nets [3, 6, 15] . In deep learning, these models are named as contrastive networks [3]...
Chapter
In this chapter, we will introduce manifold learning and graph neural networks. We hope to introduce graphical probability models as the starting point of basestone. We need to introduce our readers why we sho...
Book
Chapter
This chapter covers the fundamentals of deep learning, therefore, we present relevant knowledge in chronological order so as to fully introduce the history of deep learning development; meanwhile, we review ho...
Article
Colorectal Cancer (CRC), a leading cause of cancer-related deaths, can be abated by timely polypectomy. Computer-aided classification of polyps helps endoscopists to resect timely without submitting the sample...
Chapter
In this chapter, we will introduce the typical deep neural networks from the viewpoint of Convolutional Neural Network (CNN or ConvNet) family, especially , Single Shot MultiBox Detector (SSD) , and You Only...
Chapter
In this chapter, we introduce fundamental concepts of reinforcement learning [21] such as , , deep Q- , and double Q- . We detail why reinforcement is thought as a method of deep learning.
Article
Recently, steganalytic methods based on deep learning have achieved much better performance than traditional methods based on handcrafted features. However, most existing methods based on deep learning are spe...
Article
App responsiveness is the most intuitive interpretation of App performance from the users’ perspective. Traditional performance profilers only focus on one type of program activity (e.g., CPU profiling). In co...
Chapter and Conference Paper
This paper studies the positioning method of combining the passive electric field positioning and passive magnetic field positioning under three-dimensional (3-D) water. This technology can be applied to under...
Article
Correlation learning among different types of multimedia data, such as visual and textual content, faces huge challenges from two important perspectives, namely, cross modal and cross domain. Cross modal means th...
Book