Irina Konstantinovna Egorova · Economy Business Computer science · 2016
Algorithmic (programming) – core module of computer science, both theoretically and practically important, but also difficult. It is important to develop and apply didactic and computer software algorithms, software. In the work methods of the theory of algorithms, programming and didactics developed a system of algorithms and supporting computer system for the development, programming typical tasks processing different data structures
Cited by 0
Rainer Berkemer, Markus Grottke · AI critique · 2023
Cited by 1
Heineman, George · CERN Document Server (European Organization for Nuclear Research) · 2021
Cited by 0
Henrik Björklund, Johanna Björklund, Wim Martens · EMS Press eBooks · 2021
Cited by 4
Hermann Haken · Springer series in synergetics · 2004
Cited by 0
Phil Mars, J.R. Chen, Raghu Nambiar · 2018
Over the past decade, interest in computational or non-symbolic artificial intelligence has grown. The algorithms involved have the ability to learn from past experience, and therefore have significant potential in the adaptive control of signals and systems. This book focuses on the theory and applications of learning algorithms-stochastic learning automata; artificial neural networks; and genetic algorithms, evolutionary strategies, and evolutionary programming. Hybrid combinations of various algorithms are also discussed.Chapter 1 provides a brief overview of the topics discussed and organization of the text. The first half of the book (Chapters 2 through 4) discusses the basic theory of the learning algorithms, with one chapter devoted to each type. In the second half (Chapters 5 through 7), the emphasis is on a wide range of applications drawn from adaptive signal processing, system identification, and adaptive control problems in telecommunication networks.Learning Algorithms: Theory and Applications in Signal Processing, Control and Communications is an excellent text for final year undergraduate and first year graduate students in engineering, computer science, and related areas. Professional engineers and everyone involved in the application of learning techniques in adaptive signal processing, control, and communications will find this text a valuable synthesis of theory and practical application of the most useful algorithms.
Cited by 24
Rainer Berkemer, Markus Grottke · transcript Verlag eBooks · 2023
Cited by 1Open access
Lei, Rex · eScholarship (California Digital Library) · 2024
Reproducibility and replicability are central to the process of learning. Machine learning algorithms can solve a variety of tasks, in turn allowing researchers to ask new questions. However, reproducibility issues can limit the scope and utility of these algorithms. In this dissertation, we investigate replicability from a theoretical perspective. We formalize a new mathematical definition of replicability. Our definition applies to randomized algorithms that learn from independent and identically distributed (i.i.d.) samples. We propose replicable algorithms for fundamental learning tasks such as computing statistical queries, boosting weak learners, and learning halfspaces. We discuss techniques for designing replicable algorithms, resolving tensions among accuracy, replicability, and efficiency. Furthermore, we construct black-box algorithmic reductions between replicability and other notions of algorithmic stability, such as differential privacy. We also note possible directions for future replicability research.• The introduction is a general-audience explanation of the contents of this dissertation.• In Chapter 1, we formally introduce replicability, the central concept of this dissertation. We mathematically define replicability and the associated model, noting key features and limitations. This chapter summarizes the theorems and algorithms in the remaining chapters. We mention promising future directions and argue why researchers should pursue them. \n• In Chapter 2, we list central definitions and briefly note how they are used. The remaining three chapters are reprints of three published conference papers related to replicable learning algorithms, with readability edits.\n• In Chapter 3, we mathematically define replicability and motivate our definition. We design new replicable algorithms for fundamental learning tasks such as computing statistical queries and learning halfspaces. This chapter discusses basic properties of replicability, including alternate definitions.\n• In Chapter 4, we exhibit a paper that predates and greatly contributed to this dissertation’s work on replicability.\n• In Chapter 5, we prove strong connections between replicability and other well-studied stability notions such as differential privacy. We show black-box ways to transform certain stable algorithms to replicable algorithms and vice versa. These transformations may increase the required sample sizes and run times. We prove these increases are necessary. Applications of our connections include new replicable learning algorithms and resolving open questions in algorithmic stability.
Cited by 0Open access
Pramod Gupta, Naresh Kumar Sehgal · 2021
Cited by 0
Anwar Ali Sathio, Muhammad Malook Rind, Abdullah Lakhan · 2023
Processing and analyzing multimedia data, including photos, audio, video, and text, have been entirely changed by deep learning. This chapter gives a general introduction to deep learning, classification of deep understanding, and techniques that can be applied to grouping and categorizing multimedia data. It examines well-known clustering types and methods, including deep convolutional embedded clustering, multimodal deep embedded grouping, and convolutional autoencoders, while highlighting the difficulties in grouping multimedia data. In addition, the chapter analyzes how multimodal data and transfer learning might enhance classification performance and deep learning methods for categorizing multimedia data, such as CNNs, DBN, GAN, MLP, RNNs, ResNet, SVM, DNDT, CapsNets, and LSTMs. Examples illustrate how deep learning algorithms can cluster and categorize multimedia data effectively. The chapter also discusses blockchain technology and deep learning algorithms, cross-border blockchain definition, framework, deep learning, future directions for the field's study, and present trends.
Cited by 3
Satwik Ram Kodandaram, N. Pavan Kumar · 2019
Cited by 0Open access
Tülin İnkaya, Nur Evin Özdemirel, SİNAN KAYALIGİL · Bursa Uludag University - AVESIS · 2016
Cited by 0
Wadhah Zeyad Tareq Tareq, Mehmet Fatih Amasyalı · Elsevier eBooks · 2024
Cited by 1
Sam Waugh · 1994
This is an investigation into various strategies for changing neural network architectures which examines both the theory of changing topologies and the current literature in the area. Experiments are performed on a combination of two of the more useful methodologies, Cascade-Correlation and connection pruning, which are able to produce more compact networks.
Cited by 0
Khurana, Meenu, Thakur, Abhishek, Kantha, Praveen et al. · Communications in computer and information science · 2024
Cited by 3
Rajesh Kumar Singh, Anita Gehlot, Mahesh Kumar Prajapat et al. · Artificial Intelligence in Agriculture · 2021
Cited by 1Open access
Nathalie Japkowicz, Mohak Shah · Cambridge University Press eBooks · 2011
The field of machine learning has matured to the point where many sophisticated learning approaches can be applied to practical applications. Thus it is of critical importance that researchers have the proper tools to evaluate learning approaches and understand the underlying issues. This book examines various aspects of the evaluation process with an emphasis on classification algorithms. The authors describe several techniques for classifier performance assessment, error estimation and resampling, obtaining statistical significance as well as selecting appropriate domains for evaluation. They also present a unified evaluation framework and highlight how different components of evaluation are both significantly interrelated and interdependent. The techniques presented in the book are illustrated using R and WEKA, facilitating better practical insight as well as implementation. Aimed at researchers in the theory and applications of machine learning, this book offers a solid basis for conducting performance evaluations of algorithms in practical settings.
Cited by 738
Xavier Vasques · 2024
This book chapter covers machine learning algorithms, including linear regression, logistic regression, support vector machines (SVM), artificial neural networks (ANN), and unsupervised machine learning algorithms. It explains the mathematics behind linear regression and gradient descent optimization. Implementation details are provided for univariate and multiple linear regression. Logistic regression is discussed for both binary and multinomial cases, along with practical applications. SVM is explored for linearly separable and nonlinear data, as well as regression tasks. ANN is introduced with multilayer perceptrons (MLP), including parameter estimation and backpropagation. CNNs and RNNs, including LSTM, are discussed, along with their applications. Unsupervised learning algorithms such as k-means, mean shift, and DBSCAN are covered. The chapter concludes by introducing the application of machine learning algorithms with Hephaistos. This chapter provides a comprehensive overview of machine learning algorithms and their applications.
Cited by 3
Kumar, Atul, Amol Gawande, Darekar, Sheetal · Zenodo (CERN European Organization for Nuclear Research) · 2021
Artificial intelligence (AI) is mostly a computerized thinking area, and has always been a key part of digitization, capturing significant eyes in the computerized world. In the paper creator aims to carry out a short audit of the different AI calculations which are used most everywhere and are therefore the most relevant mainstream. In order to help educated basic leadership choose the appropriate learning calculation to satisfy the specific needs of an application, the creator expects to incorporate the advantages and defects of the AI computations from its application point of view. Assuring the complicated model is a difficult matter to address PC vision problems using small Boltzmann machines (RBMs). Many estimates for learning include relying on cross-approval or observational methods to upgrade the number of highlights. The study proposes a learning equation to find the ideal model complicated for RBMs by increasing the covered layer.
Cited by 0Open access
Aaron E. Maxwell, Christopher A. Ramezan, Yaping He · Elsevier eBooks · 2025
Cited by 0