Breaking the Mould: Rethinking Deep Learning with Unconventional Architectures | Chapter 2 | Mathematics and Computer Science: Research Updates Vol. 5

Deep learning has become the cornerstone of modern artificial intelligence, enabling breakthroughs in areas such as computer vision, natural language processing, and robotics. However, traditional deep-learning approaches face significant challenges, including data hunger, computational costs, and a lack of interpretability. This chapter explores unconventional pathways in deep learning that address these limitations and push the boundaries of AI. This paper delves into neuroevolution, spiking neural networks, capsule networks, and quantum machine learning, highlighting their unique advantages, challenges, and applications. Additionally, the study discussed the ethical considerations of these emerging technologies, emphasising the need for responsible development. By examining these unconventional approaches, this chapter aims to inspire researchers and practitioners to explore new frontiers in deep learning and unlock its full potential.

 

Author (s) Details

K. Sridhar
Department of Computer Science and Engineering, Vaageswari College of Engineering, (Autonomous) Accredited by NAAC A+, Beside L.M.D Police Station, Karimnagar, India.

Goolla Mamatha
Department of CSE(AI&ML), Vaageswari College of Engineering, (Autonomous) Accredited by NAAC A+, Beside L.M.D Police Station, Karimnagar, India.

 

Sabbani Anitha
Department of CSE, Vaageswari College of Engineering, (Autonomous) Accredited by NAAC A+, Beside L.M.D Police Station, Karimnagar, India.

 

Krishnaveni Bandari
Department of CSE, Vaageswari College of Engineering, (Autonomous) Accredited by NAAC A+, Beside L.M.D Police Station, Karimnagar, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mcsru/v5/5081

Quantum AI in Cloud Environments | Chapter 7 | Scientific Research, New Technologies and Applications Vol. 7

This paper explores the integration of Quantum Artificial Intelligence (AI) in cloud computing environments. It examines key research areas, including quantum algorithms for AI, Quantum-as-a-Service (QaaS), and serverless quantum architecture. The study highlights applications in finance, healthcare, and supply chain management, demonstrating improved computational speed and efficiency. Despite promising advancements, challenges like knowledge gaps, limited talent pool, and high costs persist. Future directions focus on addressing these challenges and expanding interdisciplinary applications. The paper concludes that Quantum AI in cloud computing offers significant potential for enhancing computational capabilities across various sectors while emphasizing the need for continued research and development.

 

Author (s) Details

Alex Mathew
Department of Cybersecurity, Bethany College, USA.

 

Please see the book here:- https://doi.org/10.9734/bpi/srnta/v7/3116

The Utilization of Quantum Computing Methods for the Implementation of Supervised Machine Learning Frameworks | Chapter 2 | Theory and Applications of Engineering Research Vol. 2

 In this place chapter, the integration of quantity computing and machine intelligence is given a lot of consideration, which will make perfect sense when used to the context of modelling quantity machine learning. The system of quantum computing lends trust to the concept of numerous machine intelligence-related endeavors as possible applications in quantity technology. The goal of quantity computing search out develop a new standard of processing that is to say fundamentally different from that of established computers. This is accomplished by combining ideas from atomic science, such as superposition and entanglement, into the calculating process. In the first part of this chapter, we accepted a high-level examine some of the principles of theory that matter is made up of atoms. In addition to that, an investigation into quantity machine learning has too been looked at in this place article. The qubit is the most fundamental component of quantity technology and plays an important function in the implementation of quantity processes in a wide range of different fields of endeavour. The use of standard calculating devices is rendered outmoded by the coming of quantum computing, that permits the resolution of issues that were previously difficult. Complicated computations refer to issues that are considerably difficult to resolve using typical calculating methods. These problems are particularly difficult to answer. Learning software that is to say based on traditional models acts incredibly well, but it creates increasing requirements for calculating power since it must handle a complex and thorough quantity of data. When posing supervised machine intelligence with quantum calculating, some of the work that must be finished includes the option of features, the encoding of limits, and the building of parameterized circuits. Topics of discourse also contain the modelling of quantum parameterized circuits, in addition to the design and implementation of quantum feature sets for sample dossier. The application of quantum processes like as superposition and complication is used to illustrate the plan of guided machine learning.

Author(s) Details:

Mukta Nivelkar,
Department of Computer Engineering and Information Technology, Veermata Jijabai Technological Institute, Mumbai, India.

S. G. Bhirud,
Department of Computer Engineering and Information Technology, Veermata Jijabai Technological Institute, Mumbai, India.

Please see the link here: https://stm.bookpi.org/TAER-V2/article/view/12945