%{search_type} search results

Annotation The Symposium series refers to all apects of theory, algorithm design, applications and emerging techniques related to computational intelligence.

• CHAPTER 1 Introduction
• CHAPTER 2 Accelerated Algorithms for Unconstrained Convex Optimization
• 1. Preliminaries
• 2. Accelerated Gradient Method for smooth optimization
• 3. Extension to the Composite Optimization
• 3.1. Nesterov's First Scheme
• 3.2. Nesterov's Second Scheme
• 3.2.1. A Primal Dual Perspective
• 3.3. Nesterov's Third Scheme
• 4. Inexact Proximal and Gradient Computing
• 4.1. Inexact Accelerated Gradient Descent
• 4.2. Inexact Accelerated Proximal Point Method
• 5. Restart
• 6. Smoothing for Nonsmooth Optimization
• 7. Higher Order Accelerated Method
• 8. Explanation: An Variational Perspective
• 8.1. Discretization
• CHAPTER 3 Accelerated Algorithms for Constrained Convex Optimization
• 1. Preliminaries
• 1.1. Case Study: Linear Equality Constraint
• 2. Accelerated Penalty Method
• 2.1. Non-strongly Convex Objectives
• 2.2. Strong Convex Objectives
• 3. Accelerated Lagrange Multiplier Method
• 3.1. Recovering the Primal Solution
• 3.2. Accelerated Augmented Lagrange Multiplier Method
• 4. Accelerated Alternating Direction Method of Multipliers
• 4.1. Non-strongly Convex and Non-smooth
• 4.2. Strongly Convex and Non-smooth
• 4.3. Non-strongly Convex and Smooth
• 4.4. Strongly Convex and Smooth
• 4.5. Non-ergodic Convergence Rate
• 4.5.1. Original ADMM
• 4.5.2. ADMM with Extrapolation and Increasing Penalty Parameter
• 5. Accelerated Primal Dual Method
• 5.1. Case 1
• 5.2. Case 2
• 5.3. Case 3
• 5.4. Case 4
• CHAPTER 4 Accelerated Algorithms for Nonconvex Optimization
• 1. Proximal Gradient with Momentum
• 1.1. Basic Assumptions
• 1.2. Convergence Theorem
• 1.3. Another Method: Monotone APG
• 2. AGD Achieves the Critical Points Quickly
• 2.1. AGD as a Convexity Monitor
• 2.2. Negative Curvature
• 2.3. Accelerating Nonconvex Optimization
• 3. AGD Escapes the Saddle Points Quickly
• 3.1. Almost Convex
• 3.2. Negative Curvature Descent
• 3.3. AGD for Non-Convex Problem
• 3.3.1. Locally Almost Convex! Globally Almost Convex
• 3.3.2. Outer Iterations
• 3.3.3. Inner Iterations
• CHAPTER 5 Accelerated Stochastic Algorithms
• 1. The Individual Convexity Case
• 1.1. Accelerated Stochastic Coordinate Descent
• 1.2. Background for Variance Reduction Methods
• 1.3. Accelerated Stochastic Variance Reduction Method
• 1.4. Black-Box Acceleration
• 2. The Individual Non-convexity Case
• 2.1. Individual Non-convex but Integrally Convex
• 3. The Non-Convexity Case
• 3.1. SPIDER
• 3.2. Momentum Acceleration
• 4. Constrained Problem
• 5. Infinity Case
• CHAPTER 6 Paralleling Algorithms
• 1. Accelerated Asynchronous Algorithms
• 1.1. Asynchronous Accelerated Gradient Descent
• 1.2. Asynchronous Accelerated Stochastic Coordinate Descent
• 2. Accelerated Distributed Algorithms
• 2.1. Centralized Topology
• 2.1.1. Large Mini-batch Algorithms
• 2.1.2. Dual Communication-Efficient Methods
• 2.2. Decentralized Topology
• CHAPTER 7 Conclusions
• APPENDIX Mathematical Preliminaries.
• (source: Nielsen Book Data)

This book on optimization includes forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo. Machine learning relies heavily on optimization to solve problems with its learning models, and first-order optimization algorithms are the mainstream approaches. The acceleration of first-order optimization algorithms is crucial for the efficiency of machine learning. Written by leading experts in the field, this book provides a comprehensive introduction to, and state-of-the-art review of accelerated first-order optimization algorithms for machine learning. It discusses a variety of methods, including deterministic and stochastic algorithms, where the algorithms can be synchronous or asynchronous, for unconstrained and constrained problems, which can be convex or non-convex. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference resource for users who are seeking faster optimization algorithms, as well as for graduate students and researchers wanting to grasp the frontiers of optimization in machine learning in a short time.
(source: Nielsen Book Data)

• Introduction.- Part 1:Background and Methodology.- Discrete Consensus Achievement in Artificial Systems.- Modular Design of Strategies for the Best-of-n Problem.- Part 2:Mathematical Modeling and Analysis.- Indirect Modulation of Majority-Based Decisions.- Direct Modulation of Voter-Based Decisions.- Direct Modulation of Majority-Based Decisions.- Part 3:Robot Experiments.- A Robot Experiment in Site Selection.- A Robot Experiment in Collective Perception.- Part 4:Discussion and Annexes.- Conclusions.- Background on Markov Chains.
• (source: Nielsen Book Data)

This book focuses on the design and analysis of collective decision-making strategies for the best-of-n problem. After providing a formalization of the structure of the best-of-n problem supported by a comprehensive survey of the swarm robotics literature, it introduces the functioning of a collective decision-making strategy and identifies a set of mechanisms that are essential for a strategy to solve the best-of-n problem. The best-of-n problem is an abstraction that captures the frequent requirement of a robot swarm to choose one option from of a finite set when optimizing benefits and costs. The book leverages the identification of these mechanisms to develop a modular and model-driven methodology to design collective decision-making strategies and to analyze their performance at different level of abstractions. Lastly, the author provides a series of case studies in which the proposed methodology is used to design different strategies, using robot experiments to show how the designed strategies can be ported to different application scenarios.
(source: Nielsen Book Data)

• Automating Inquiry Uncertainty Sampling Searching Through the Hypothesis Space Minimizing Expected Error and Variance Exploiting Structure in Data Theory Practical Considerations.
• (source: Nielsen Book Data)

The key idea behind active learning is that a machine learning algorithm can perform better with less training if it is allowed to choose the data from which it learns. An active learner may pose ""queries, "" usually in the form of unlabeled data instances to be labeled by an ""oracle"" (e.g., a human annotator) that already understands the nature of the problem. This sort of approach is well-motivated in many modern machine learning and data mining applications, where unlabeled data may be abundant or easy to come by, but training labels are difficult, time-consuming, or expensive to obtain. This book is a general introduction to active learning. It outlines several scenarios in which queries might be formulated, and details many query selection algorithms which have been organized into four broad categories, or ""query selection frameworks."" We also touch on some of the theoretical foundations of active learning, and conclude with an overview of the strengths and weaknesses of these approaches in practice, including a summary of ongoing work to address these open challenges and opportunities.
(source: Nielsen Book Data)

• Part I: Basics and Theory
• Photometry
• Geometry
• Sensors
• Light Sources
• Part II: Algorithms Photometric stereo
• Structured light
• Other shape reconstruction techniques
• Photometric estimation Part III: Applications
• Visualization, Augmented Reality, Virtual Reality, and Mixed Reality Systems
• Biomedical Applications
• E-Heritage
• Robot Vision, Autonomous Vehicles, and Humans.
• (source: Nielsen Book Data)

This book describes active illumination techniques in computer vision. We can classify computer vision techniques into two classes: passive and active techniques. Passive techniques observe the scene statically and analyse it as is. Active techniques give the scene some actions and try to facilitate the analysis. In particular, active illumination techniques project specific light, for which the characteristics are known beforehand, to a target scene to enable stable and accurate analysis of the scene. Traditional passive techniques have a fundamental limitation. The external world surrounding us is three-dimensional; the image projected on a retina or an imaging device is two-dimensional. That is, reduction of one dimension has occurred. Active illumination techniques compensate for the dimensional reduction by actively controlling the illumination. The demand for reliable vision sensors is rapidly increasing in many application areas, such as robotics and medical image analysis. This book explains this new endeavour to explore the augmentation of reduced dimensions in computer vision. This book consists of three parts: basic concepts, techniques, and applications. The first part explains the basic concepts for understanding active illumination techniques. In particular, the basic concepts of optics are explained so that researchers and engineers outside the field can understand the later chapters. The second part explains currently available active illumination techniques, covering many techniques developed by the authors. The final part shows how such active illumination techniques can be applied to various domains, describing the issue to be overcome by active illumination techniques and the advantages of using these techniques. This book is primarily aimed at 4th year undergraduate and 1st year graduate students, and will also help engineers from fields beyond computer vision to use active illumination techniques. Additionally, the book is suitable as course material for technical seminars.
(source: Nielsen Book Data)

• Cover; Title page; Preface; Acknowledgments; Contents; I. Data Collection; Toward Active Mining from On-line Scientific Text Abstracts Using Pre-existing Sources; Data Mining on the WAVEs
• Word-of-mouth-Assisting Virtual Environments; Immune Network-based Clustering for WWW Information Gathering/Visualization; Interactive Web Page Retrieval with Relational Learning-based Filtering Rules; Monitoring Partial Update of Web Pages by Interactive Relational Learning; Context-based Classification of Technical Terms Using Support Vector Machines.

Focusing on data mining, this work is a joint effort from researchers in Japan, and includes a report on the forefront of data collection, user-centred mining and user interaction/reaction. It offers an overview of modern solutions with real-world applications, sharing hard-learned experiences.

• Introduction.- RelatedWork and Background.- Theoretical Analysis of Differential Evolution.- Parameter Adaptive Differential Evolution.- Surrogate Model-based Differential Evolution.- Adaptive Multi-Objective Differential Evolution.- Application to Winner Determination Problems in Combinatorial Auctions.- Application to Flight Planning in Air Traffic Control Systems.- Application to the TPM Optimization in Credit Decision Making.- Conclusions and Future Work.
• (source: Nielsen Book Data)

Optimization problems are ubiquitous in academic research and real-world applications wherever such resources as space, time and cost are limited. Researchers and practitioners need to solve problems fundamental to their daily work which, however, may show a variety of challenging characteristics such as discontinuity, nonlinearity, nonconvexity, and multimodality. It is expected that solving a complex optimization problem itself should easy to use, reliable and efficient to achieve satisfactory solutions. Differential evolution is a recent branch of evolutionary algorithms that is capable of addressing a wide set of complex optimization problems in a relatively uniform and conceptually simple manner. For better performance, the control parameters of differential evolution need to be set appropriately as they have different effects on evolutionary search behaviours for various problems or at different optimization stages of a single problem. The fundamental theme of the book is theoretical study of differential evolution and algorithmic analysis of parameter adaptive schemes. Topics covered in this book include: Theoretical analysis of differential evolution and its control parameters Algorithmic design and comparative analysis of parameter adaptive schemes Scalability analysis of adaptive differential evolution Adaptive differential evolution for multi-objective optimization Incorporation of surrogate model for computationally expensive optimization Application to winner determination in combinatorial auctions of E-Commerce Application to flight route planning in Air Traffic Management Application to transition probability matrix optimization in credit-decision making.

• Adaptive Instruction Design and Authoring.- Interoperability and Standardization in Adaptive Instructional Systems.- Instructional Theories in Adaptive Instruction.- Learner Assessment and Modelling.- AI in Adaptive Instructional Systems, Conversational Tutors.
• (source: Nielsen Book Data)

This book constitutes the refereed proceedings of the First International Conference on Adaptive Instructional Systems, AIS 2019, held in July 2019 as part of HCI International 2019 in Orlando, FL, USA. HCII 2019 received a total of 5029 submissions, of which 1275 papers and 209 posters were accepted for publication after a careful reviewing process. The 50 papers presented in this volume are organized in topical sections named: Adaptive Instruction Design and Authoring, Interoperability and Standardization in Adaptive Instructional Systems, Instructional Theories in Adaptive Instruction, Learner Assessment and Modelling, AI in Adaptive Instructional Systems, Conversational Tutors.
(source: Nielsen Book Data)

• Designing and Developing Adaptive Instructional Systems.- Sensor-based Adaptive Instructional Systems in Live Simulation Training.- An Ambient & Pervasive Personalized Learning Ecosystem: "Smart Learning" in the Age of the Internet of Things.- Bridging Conceptual Models and Architectural Interchange for Adaptive Instructional Systems.- Dewey's Ethics of Moral Principles and Deliberation: Extending IEEE's Ethics Initiative for Adaptive Instructional Systems.- Realistic and Relevant Role-Players for Experiential Learning.- Learning Traces, Measurement and Assessment Templates for AIS Interoperability.- Supporting different Roles and Responsibilities in Developing and Using Context-based Adaptive Personalized Collaboration Environments Compliant to the Law.- Experiential Instruction of Metacognitive Strategies.- Falling Forward: Lessons Learned from Real-Life Implementation of Adaptive Learning Solutions.- Usability Dimensions of Simulated Trainers for Buried Explosives.- Toward Zero Authoring: Considering How to Maximize Courseware Quality and Affordability Simultaneously.- Agent-Based Methods in Support of Adaptive Instructional Decisions.- Representing Functional Relationships of Adaptive Instructional Systems in a Conceptual Model.- Knowledge-to-Information Translation Training (KITT): An Adaptive Approach to Explainable Artificial Intelligence.- User Rights and Adaptive A/IS - From Passive Interaction to Real Empowerment.- Supporting Metacognitive Learning Strategies through an Adaptive Application.- Towards Iteration by Design: An Interaction Design Concept for Safety Critical Systems.- Learner Modelling and Methods of Adaptation.- Bayesian Student Modelling in the AC&NL Tutor.- Nature at Your Service - Nature Inspired Representations Combined with Eye-gaze Features to Infer User Attention and Provide Contextualized Support.- Adapting Instruction by Measuring Engagement with Machine Learning in Virtual Reality Training.- Realizing the Promise of AI-Powered, Adaptive, Automated, Instant Feedback on Writing for Students in Grade 3-8 with an IEP.- Declarative Knowledge Extraction in the AC&NL Tutor.- On the Importance of Adaptive Operator Training in Human-Swarm Interaction.- The Mental Machine: Classifying Mental Workload State from Unobtrusive Heart Rate- measures Using Machine Learning.- Production Implementation of Recurrent Neural Networks in Adaptive Instructional Systems.- Pilot State Monitoring for Cursus Recommendation.- Experimental Evaluation of Heart-based Workload Measures as Related to Their Suitability for Real-time Applications.- EEG Covariance-based Estimation of Cooperative States in Teammates.- Adapting the Zone of Proximal Development to the Wicked Environments of Professional Practice.- An Adaptive Instructional System for the Retention of Complex Skills.- Learner Modeling in the Context of Caring Assessments.- Evaluating the Effectiveness of Adaptive Instructional Systems.- The Evolving Assessment Landscape and Adaptive Instructional Systems: Moving Beyond Good Intentions.- Contextual Barriers to Validity in Adaptive Instruction and Assessment.- Does Time Matter in Learning? A Computer Simulation of Carroll's Model of Learning.- Competency Development through Experiential Training: Mapping Scenarios with Assessments.- Does Gamification Work? Analyzing Effects of Game Features on Learning in an Adaptive Scenario-Based Trainer.- From "Knowing What" to "Knowing When": Exploring a Concept of Situation Awareness Synchrony for Evaluating SA Dynamics in Teams.- Exploring Video Engagement in an Intelligent Tutoring System.- Using a Non-Player Character to Improve Training Outcomes for Submarine Electronic Warfare Operators.- The Impact of Adaptive Activities in Acrobatiq Courseware: Investigating the Efficacy of Formative Adaptive Activities on Learning Estimates and Summative Assessment Scores.- A Mastery Approach to Flashcard-based Adaptive Training. .
• (source: Nielsen Book Data)

This volume constitutes the refereed proceedings of the Second International Conference on Adaptive Instructional Systems, AIS 2020, which was due to be held in July 2020 as part of HCI International 2020 in Copenhagen, Denmark. The conference was held virtually due to the COVID-19 pandemic. A total of 1439 papers and 238 posters have been accepted for publication in the HCII 2020 proceedings from a total of 6326 submissions. The 41 papers presented in this volume were organized in topical sections as follows: designing and developing adaptive instructional systems; learner modelling and methods of adaptation; evaluating the effectiveness of adaptive instructional systems. Chapter "Exploring Video Engagement in an Intelligent Tutoring System" is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.
(source: Nielsen Book Data)