Computing Technologies and Applications

Paving Path Towards Society 5.0

Latesh Malik, Sandhya Arora, Urmila Shrawankar, Maya Ingle, Indu Bhagat, Latesh Malik, Sandhya Arora, Urmila Shrawankar, Maya Ingle, Indu Bhagat

• Éditeur: Chapman and Hall/CRC
• Année: 2021
• ISBN:
  9781000473513
• Édition: 1
• Sujet: Computer Science
• Sous-sujet: Data Mining

Making use of digital technology for social care is a major responsibility of the computing domain. Social care services require attention for ease in social systems, e-farming, and automation, etc.

Thus, the book focuses on suggesting software solutions for supporting social issues, such as health care, learning about and monitoring for disabilities, and providing technical solutions for better living. Technology is enabling people to have access to advances so that they can have better health.

To undergo the digital transformation, the current processes need to be completely re-engineered to make use of technologies like the Internet of Things (IoT), big data analytics, artificial intelligence, and others. Furthermore, it is also important to consider digital initiatives in tandem with their cloud strategy instead of treating them in isolation.

At present, the world is going through another, possibly even stronger revolution: the use of recent computing models to perform complex cognitive tasks to solve social problems in ways that were previously either highly complicated or extremely resource intensive.

This book not only focuses the computing technologies, basic theories, challenges, and implementation but also covers case studies. It focuses on core theories, architectures, and technologies necessary to develop and understand the computing models and their applications. The book also has a high potential to be used as a recommended textbook for research scholars and post-graduate programs.

• The book deals with a problem-solving approach using recent tools and technology for problems in health care, social care, etc.

• 
  
  

• Interdisciplinary studies are emerging as both necessary and practical in universities.

• 
  
  

• This book helps to improve computational thinking to "understand and change the world'. It will be a link between computing and a variety of other fields.

• 
  
  

• Case studies on social aspects of modern societies and smart cities add to the contents of the book to enhance book adoption potential.

This book will be useful to undergraduates, postgraduates, researchers, and industry professionals. Every chapter covers one possible solution in detail, along with results.

Section III Data Science, Deep Learning, and Machine Learning

9 Stochastic Computing for Deep Neural Networks

Sunny Bodiwala¹ and Nirali Nanavati²

¹Gujarat Technological University, Ahmedabad, Gujarat, India

²Sarvajanik College of Engineering and Technology, Surat, Gujarat, India

DOI: 10.1201/9781003166702-9

9.1 Introduction

Humans have always aspired to create machines that think. People are inclined toward intelligent systems for automating routine labor, speech and image recognition, disease diagnosis, developing self-driving motors, etc. The ability of an artificial intelligence (AI) framework to gain knowledge on its own, by extracting important information from data, is machine learning [1]. Deep learning has arisen as another zone of AI research that permits a machine to consequently gain complex capacities straightforwardly from the information by removing portrayals at numerous degrees of deliberation [2]. Deep neural networks (DNNs) have accomplished remarkable progress in many AI applications, for example, discourse acknowledgment [3] and object detection [4]. Albeit such undertakings are instinctively settled by humans, they initially demonstrated to be a genuine test to computerized reasoning.

In spite of their success, when contrasted with other AI techniques, DNNs require more calculations because of the deep architectural model. Besides, developer’s desire for better execution will in general increase the size of the models, prompting longer training and testing time just as more computational resources are required for execution. The overall accuracy of these models depends on the utilization of high-performance infrastructure to implement DNNs. However, high-performance cloud infrastructure incurs huge power utilization and a huge equipment cost, accordingly restricting their deployment for low-cost and low-power applications, for example, implanted and wearable gadgets that need low power and small hardware [5]. Such applications progressively use AI algorithms to perform essential tasks, for example, speech-to-text transcription, natural language processing, and image and video recognition [2,6]. Subsequently, to implement such models in resource constraint frameworks, an alternative option should be found. At times, specific equipment has been designed utilizing Application Specific Integrated Circuits (ASICs) and Field Programmable Gate Arrays (FPGAs) [5,7]. All things considered, an edge of progress exists if the internal structure of models is additionally modified.

Stochastic computing (SC) as an important option in contrast to binary computing is considered in this chapter. SC works on arbitrary bit sequences, in which probabilities are given by the likelihood of a self-assertive bit in the grouping being one. This portrayal is especially alluring as it empowers minimal overhead implementation of key arithmetic units utilizing basic rationale circuits [8]. For instance, addition and multiplication can be performed utilizing a multiplexer (MUX) and an AND gate individually. Stochastic processing offers an extremely low hardware footprint, high level of error resilience, and the capacity to compromise calculation time and exactness with no extra hardware changes [9]. It subsequently can possibly actualize DNNs with fundamentally diminished hardware impression and low cost utilization. SC has a few drawbacks, including accuracy issues because of the inborn fluctuation in assessing the likelihood spoke by stochastic grouping. Besides, sudden increment in the accuracy of a stochastic implementation requires an outstanding expansion of bit stream length [8], consequently expanding the general computation. The more reasonable consideration will be stochastic arithmetic for the application where the precision necessities in the separate calculations are moderately low.

DNNs are described by a characteristic error tolerance, which recognizes them from other AI strategies that require exact calculations and a definite number portrayals. Moreover, Bishop [10] and Murray and Edwards [11] show that the expansion of clamor during the preparation of a neural model improves the model's performance. Designers can naturally support this error tolerance by thinking about the variation of the inclination drop calculation, the stochastic angle drop that is broadly utilized for preparing DNNs. The technique of stochastic inclination drop gives an impartial gauge of the genuine angle dependent on a bunch of tests. By this, the randomization appears to profit the minimization of the target work as it permits a getaway from the local minima.

9.2 Theoretical Background

Literature review is given in this part of the chapter. Related work and deep neural networks are also presented, with subsequent introduction of essential standards of computerized and stochastic math.

9.2.1 Related Work

Neural networks have existed for a long time. Notwithstanding, until the beginning of the 21st century, where progresses in innovation of hardware empowered the improvement of competent models. Indeed, DNN training is constrained by the accessible computation even today.

CPUs are all in all incapable of giving enough calculation ability to prepare enormous-scale DNNs. These days, GPUs are the default decision for DNN deployment because of the high computation power and simplicity to utilize advanced frameworks [12]. Facebook AI Group have [13] trained a convolutional neural network (CNN) on multiple GPU. Wen et al. [14] examined the memory effectiveness of different layers of CNN and uncovered exhibition suggestions from data formats and memory access designs. Finally, Cao et al. [15] proposed an execution of a cellular-deep neural network on GPU, a local recurrent neural model (RNN) that...