Information Processing Letters, ISSN 0020-0190, 2010, Volume 111, Issue 1, pp. 40 - 45

In this paper, we study the quantum PAC learning model, offering an improved lower bound on the query complexity. For a concept class with VC dimension d, the...

PAC (Probably Approximately Correct) learning | Lower bound | Quantum algorithm | VC dimension | Computational complexity | COMPUTER SCIENCE, INFORMATION SYSTEMS | learning | PAC (Probably Approximately Correct) | Analysis | Algorithms | Learning | Lower bounds | Accuracy | Query processing | Confidence | Images | Complexity

PAC (Probably Approximately Correct) learning | Lower bound | Quantum algorithm | VC dimension | Computational complexity | COMPUTER SCIENCE, INFORMATION SYSTEMS | learning | PAC (Probably Approximately Correct) | Analysis | Algorithms | Learning | Lower bounds | Accuracy | Query processing | Confidence | Images | Complexity

Journal Article

IEEE Transactions on Neural Networks and Learning Systems, ISSN 2162-237X, 02/2015, Volume 26, Issue 2, pp. 346 - 356

In this paper, the first probably approximately correct (PAC) algorithm for continuous deterministic systems without relying on any system dynamics is...

Algorithm design and analysis | Learning systems | Efficient exploration | Upper bound | probably approximately correct (PAC) | Heuristic algorithms | Approximation algorithms | Polynomials | Partitioning algorithms | state aggregation | reinforcement learning (RL) | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | ZERO-SUM GAMES | TIME NONLINEAR-SYSTEMS | CONTROL SCHEME | COMPUTER SCIENCE, THEORY & METHODS | MODEL-BASED EXPLORATION | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | ENGINEERING, ELECTRICAL & ELECTRONIC | Learning | Policies | Algorithms | Computer simulation | Neural networks | Dynamics | Mathematical analysis | Exploration | Dynamical systems

Algorithm design and analysis | Learning systems | Efficient exploration | Upper bound | probably approximately correct (PAC) | Heuristic algorithms | Approximation algorithms | Polynomials | Partitioning algorithms | state aggregation | reinforcement learning (RL) | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | ZERO-SUM GAMES | TIME NONLINEAR-SYSTEMS | CONTROL SCHEME | COMPUTER SCIENCE, THEORY & METHODS | MODEL-BASED EXPLORATION | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | ENGINEERING, ELECTRICAL & ELECTRONIC | Learning | Policies | Algorithms | Computer simulation | Neural networks | Dynamics | Mathematical analysis | Exploration | Dynamical systems

Journal Article

IEEE Transactions on Communications, ISSN 0090-6778, 09/2018, Volume 66, Issue 9, pp. 3837 - 3847

Content caching at the small-cell base stations (sBSs) in a heterogeneous wireless network is considered. A cost function is proposed that captures the...

Wireless communication | Base stations | Analytical models | probably approximately correct (PAC) learning | Protocols | time-varying popularity profiles | Caching | Loss measurement | Electronic mail | Complexity theory | TELECOMMUNICATIONS | SMALL-CELL | DELIVERY | ENGINEERING, ELECTRICAL & ELECTRONIC | Wireless networks | Computer simulation | Radio equipment

Wireless communication | Base stations | Analytical models | probably approximately correct (PAC) learning | Protocols | time-varying popularity profiles | Caching | Loss measurement | Electronic mail | Complexity theory | TELECOMMUNICATIONS | SMALL-CELL | DELIVERY | ENGINEERING, ELECTRICAL & ELECTRONIC | Wireless networks | Computer simulation | Radio equipment

Journal Article

4.
Full Text
A Lockdown Technique to Prevent Machine Learning on PUFs for Lightweight Authentication

IEEE Transactions on Multi-Scale Computing Systems, ISSN 2332-7766, 07/2016, Volume 2, Issue 3, pp. 146 - 159

We present a lightweight PUF-based authentication approach that is practical in settings where a server authenticates a device, and for use cases where the...

computationally unrestricted adversary | probably approximately correct (PAC) learning | Protocols | Authentication | Physical unclonable function | heuristic security | Silicon | Manufacturing | Servers | Cryptography | machine learning | authentication

computationally unrestricted adversary | probably approximately correct (PAC) learning | Protocols | Authentication | Physical unclonable function | heuristic security | Silicon | Manufacturing | Servers | Cryptography | machine learning | authentication

Journal Article

Machine Learning, ISSN 0885-6125, 3/2011, Volume 82, Issue 3, pp. 399 - 443

We introduce a learning framework that combines elements of the well-known PAC and mistake-bound models. The KWIK (knows what it knows) framework was designed...

Mistake bound | Control , Robotics, Mechatronics | Active learning | Reinforcement learning | Computing Methodologies | Simulation and Modeling | Exploration | Computational learning theory | Knows What It Knows (KWIK) | Computer Science | Artificial Intelligence (incl. Robotics) | Probably Approximately Correct (PAC) | Language Translation and Linguistics | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Computer science | Analysis | Computer programming | Artificial intelligence

Mistake bound | Control , Robotics, Mechatronics | Active learning | Reinforcement learning | Computing Methodologies | Simulation and Modeling | Exploration | Computational learning theory | Knows What It Knows (KWIK) | Computer Science | Artificial Intelligence (incl. Robotics) | Probably Approximately Correct (PAC) | Language Translation and Linguistics | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Computer science | Analysis | Computer programming | Artificial intelligence

Journal Article

IEEE Transactions on Information Theory, ISSN 0018-9448, 12/2002, Volume 48, Issue 12, pp. 3140 - 3150

We present a bound on the generalization error of linear classifiers in terms of a refined margin quantity on the training sample. The result is obtained in a...

Support vector machines | Codes | Vector quantization | Kelvin | Lattices | Silicon | Error correction | Generalization error bound | Gibbs classification strategy | Model selection | Computational learning theory | Bayes classification strategy | Linear classifiers | Probably approximately correct (PAC)-Bayesian framework | Margin | volume ratios | linear classifiers | margin | support vector machine (SVM) | model selection | COMPUTER SCIENCE, INFORMATION SYSTEMS | computational learning theory | ENGINEERING, ELECTRICAL & ELECTRONIC | probably approximately correct (PAC)-Bayesian framework | generalization error bound | UNIFORM-CONVERGENCE | Bayesian statistical decision theory | Usage | Approximation theory | Learning, Psychology of | Research | Gibbs' equation | Training | Classifiers | Errors | Mathematical analysis | Inverse | Mathematical models | Vectors (mathematics)

Support vector machines | Codes | Vector quantization | Kelvin | Lattices | Silicon | Error correction | Generalization error bound | Gibbs classification strategy | Model selection | Computational learning theory | Bayes classification strategy | Linear classifiers | Probably approximately correct (PAC)-Bayesian framework | Margin | volume ratios | linear classifiers | margin | support vector machine (SVM) | model selection | COMPUTER SCIENCE, INFORMATION SYSTEMS | computational learning theory | ENGINEERING, ELECTRICAL & ELECTRONIC | probably approximately correct (PAC)-Bayesian framework | generalization error bound | UNIFORM-CONVERGENCE | Bayesian statistical decision theory | Usage | Approximation theory | Learning, Psychology of | Research | Gibbs' equation | Training | Classifiers | Errors | Mathematical analysis | Inverse | Mathematical models | Vectors (mathematics)

Journal Article

Journal of Computer and System Sciences, ISSN 0022-0000, 2005, Volume 70, Issue 4, pp. 471 - 484

We study a model of probably exactly correct (PExact) learning that can be viewed either as the Exact model (learning from equivalence queries only) relaxed so...

Probably approximately correct learning | Computational learning theory | Exact learning | Parallel learning | Machine learning | probably approximately correct learning | CIRCUITS | parallel learning | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | computational learning theory | exact learning | COMPUTER SCIENCE, THEORY & METHODS | machine learning | Computer science | Analysis

Probably approximately correct learning | Computational learning theory | Exact learning | Parallel learning | Machine learning | probably approximately correct learning | CIRCUITS | parallel learning | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | computational learning theory | exact learning | COMPUTER SCIENCE, THEORY & METHODS | machine learning | Computer science | Analysis

Journal Article

IEEE Transactions on Signal Processing, ISSN 1053-587X, 04/2012, Volume 60, Issue 4, pp. 1833 - 1848

In a cognitive radio network, opportunistic spectrum access (OSA) to the underutilized spectrum involves not only sensing the spectrum occupancy but also...

opportunistic spectrum access (OSA) | Rayleigh channels | Throughput | Complexity theory | Active spectrum sensing | Cognitive radio | multiarmed bandit problem (MABP) | probably approximately correct (PAC) learning | diversity | energy allocation | median elimination algorithm (MEA) | Sensors | Data communication | cognitive radio | NETWORKS | ALGORITHMS | ENGINEERING, ELECTRICAL & ELECTRONIC | ORDER | EXPLORATION | OPTIMALITY | MULTIARMED BANDIT | MEDIUM ACCESS | Fading channels | Technology application | Energy consumption | Usage | Mathematical optimization | Methods | Studies | Networks | Allocations | Energy transmission | Data transmission | Detection | Channels | Optimization

opportunistic spectrum access (OSA) | Rayleigh channels | Throughput | Complexity theory | Active spectrum sensing | Cognitive radio | multiarmed bandit problem (MABP) | probably approximately correct (PAC) learning | diversity | energy allocation | median elimination algorithm (MEA) | Sensors | Data communication | cognitive radio | NETWORKS | ALGORITHMS | ENGINEERING, ELECTRICAL & ELECTRONIC | ORDER | EXPLORATION | OPTIMALITY | MULTIARMED BANDIT | MEDIUM ACCESS | Fading channels | Technology application | Energy consumption | Usage | Mathematical optimization | Methods | Studies | Networks | Allocations | Energy transmission | Data transmission | Detection | Channels | Optimization

Journal Article

Discrete Event Dynamic Systems, ISSN 0924-6703, 9/2007, Volume 17, Issue 3, pp. 307 - 327

This paper considers the problem of computing an optimal policy for a Markov decision process, under lack of complete a priori knowledge of (1) the branching...

Markov decision processes | Uncertainty management | Systems Theory, Control | Convex and Discrete Geometry | Operations Research/Decision Theory | Machine learning | Ranking & selection | Manufacturing, Machines, Tools | Mathematics | Computational learning theory | Efficient probably approximately correct (PAC) algorithms | Electronic and Computer Engineering | MATHEMATICS, APPLIED | OPERATIONS RESEARCH & MANAGEMENT SCIENCE | ranking & selection | UNCERTAINTY | computational learning theory | machine learning | efficient probably approximately correct (PAC) algorithms | uncertainty management | AUTOMATION & CONTROL SYSTEMS | Algorithms

Markov decision processes | Uncertainty management | Systems Theory, Control | Convex and Discrete Geometry | Operations Research/Decision Theory | Machine learning | Ranking & selection | Manufacturing, Machines, Tools | Mathematics | Computational learning theory | Efficient probably approximately correct (PAC) algorithms | Electronic and Computer Engineering | MATHEMATICS, APPLIED | OPERATIONS RESEARCH & MANAGEMENT SCIENCE | ranking & selection | UNCERTAINTY | computational learning theory | machine learning | efficient probably approximately correct (PAC) algorithms | uncertainty management | AUTOMATION & CONTROL SYSTEMS | Algorithms

Journal Article

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, ISSN 1003-6059, 10/2014, Volume 27, Issue 10, pp. 865 - 872

Journal Article

Journal of Computer and System Sciences, ISSN 0022-0000, 2004, Volume 68, Issue 3, pp. 521 - 545

This paper considers a modification of a PAC learning theory problem in which each instance of the training data is supplemented with side information. In this...

Uniform convergence of empirical means | Learning theory | Dependent data | Probably Approximately Correct learning | probably approximately correct learning | dependent data | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | HINTS | DIMENSION | SYSTEMS | COMPUTER SCIENCE, THEORY & METHODS | learning theory | uniform convergence of empirical means

Uniform convergence of empirical means | Learning theory | Dependent data | Probably Approximately Correct learning | probably approximately correct learning | dependent data | COMPUTER SCIENCE, HARDWARE & ARCHITECTURE | HINTS | DIMENSION | SYSTEMS | COMPUTER SCIENCE, THEORY & METHODS | learning theory | uniform convergence of empirical means

Journal Article

Machine Learning, ISSN 0885-6125, 5/2002, Volume 47, Issue 2, pp. 133 - 151

We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and...

probably approximately correct learning | linear threshold functions | boosting | Automation and Robotics | Computer Science | Artificial Intelligence (incl. Robotics) | Computer Science, general | Probably approximately correct learning | Boosting | Linear threshold functions | POLYNOMIAL-TIME | BOUNDS | ALGORITHM | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Algorithms | Studies

probably approximately correct learning | linear threshold functions | boosting | Automation and Robotics | Computer Science | Artificial Intelligence (incl. Robotics) | Computer Science, general | Probably approximately correct learning | Boosting | Linear threshold functions | POLYNOMIAL-TIME | BOUNDS | ALGORITHM | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | Algorithms | Studies

Journal Article

IEEE Transactions on Information Theory, ISSN 0018-9448, 10/2002, Volume 48, Issue 10, pp. 2721 - 2735

Generalization bounds depending on the margin of a classifier are a relatively new development. They provide an explanation of the performance of...

Learning systems | Probability | Neural networks | Statistics | Gaussian processes | Ridge regression | Probably approximately correct (pac) learning | Statistical learning | Margin distribution | Support vector machines (SVMs) | Soft margin | Generalization | Margin | margin | statistical learning | NUMBERS | neural networks | ridge regression | COMPUTER SCIENCE, INFORMATION SYSTEMS | NETWORKS | margin distribution | ENGINEERING, ELECTRICAL & ELECTRONIC | soft margin | generalization | probably approximately correct (pac) learning | support vector machines (SVMs) | Database administration | Research | Information storage and retrieval systems | Analysis | Information theory | Support vector machines | Classifiers | Algorithms | Regression | Gaussian | Robustness | Regression analysis

Learning systems | Probability | Neural networks | Statistics | Gaussian processes | Ridge regression | Probably approximately correct (pac) learning | Statistical learning | Margin distribution | Support vector machines (SVMs) | Soft margin | Generalization | Margin | margin | statistical learning | NUMBERS | neural networks | ridge regression | COMPUTER SCIENCE, INFORMATION SYSTEMS | NETWORKS | margin distribution | ENGINEERING, ELECTRICAL & ELECTRONIC | soft margin | generalization | probably approximately correct (pac) learning | support vector machines (SVMs) | Database administration | Research | Information storage and retrieval systems | Analysis | Information theory | Support vector machines | Classifiers | Algorithms | Regression | Gaussian | Robustness | Regression analysis

Journal Article

06/2011, ISBN 9780470641835, 9

Book Chapter

IEEE Transactions on Image Processing, ISSN 1057-7149, 08/2004, Volume 13, Issue 8, pp. 1136 - 1146

This paper presents a new, accurate, and efficient technique to increase the spatial resolution of binary halftone images. It makes use of a machine learning...

Printing | Process design | Image resolution | Machine learning | Gray-scale | Probability | Decision trees | Printers | Spatial resolution | Pixel | probably approximately correct (PAC) learning | halftoning | DIFFUSION | OPERATORS | resolution increasing | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | decision tree learning | inverse halftoning | ENGINEERING, ELECTRICAL & ELECTRONIC | Likelihood Functions | Reproducibility of Results | Algorithms | Artificial Intelligence | Image Interpretation, Computer-Assisted - methods | Sensitivity and Specificity | Signal Processing, Computer-Assisted | Image Enhancement - methods | Decision Trees | Models, Statistical | Pattern Recognition, Automated | Subtraction Technique | Signal processing | Decision tree | Analysis | Studies

Printing | Process design | Image resolution | Machine learning | Gray-scale | Probability | Decision trees | Printers | Spatial resolution | Pixel | probably approximately correct (PAC) learning | halftoning | DIFFUSION | OPERATORS | resolution increasing | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | decision tree learning | inverse halftoning | ENGINEERING, ELECTRICAL & ELECTRONIC | Likelihood Functions | Reproducibility of Results | Algorithms | Artificial Intelligence | Image Interpretation, Computer-Assisted - methods | Sensitivity and Specificity | Signal Processing, Computer-Assisted | Image Enhancement - methods | Decision Trees | Models, Statistical | Pattern Recognition, Automated | Subtraction Technique | Signal processing | Decision tree | Analysis | Studies

Journal Article

Neural Computing and Applications, ISSN 0941-0643, 5/2015, Volume 26, Issue 4, pp. 775 - 787

This paper proposes a probably approximately correct (PAC) algorithm that directly utilizes online data efficiently to solve the optimal control problem of...

Computational Biology/Bioinformatics | Probably approximately correct | Computer Science | Data Mining and Knowledge Discovery | Image Processing and Computer Vision | Reinforcement learning | Artificial Intelligence (incl. Robotics) | Kd-tree | Computational Science and Engineering | Probability and Statistics in Computer Science | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | TIME NONLINEAR-SYSTEMS | Data mining | Algorithms | Machine learning

Computational Biology/Bioinformatics | Probably approximately correct | Computer Science | Data Mining and Knowledge Discovery | Image Processing and Computer Vision | Reinforcement learning | Artificial Intelligence (incl. Robotics) | Kd-tree | Computational Science and Engineering | Probability and Statistics in Computer Science | COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE | TIME NONLINEAR-SYSTEMS | Data mining | Algorithms | Machine learning

Journal Article

Dissertation

One of the main criticisms of previously studied label noise models in the PAC-learning framework is the inability of such models to represent the noise in...

PAC learning, label noise, minimum disagreement strategy, binary classification | noise, class noise, PAC, probably approximately correct

PAC learning, label noise, minimum disagreement strategy, binary classification | noise, class noise, PAC, probably approximately correct

Dissertation

2010, Lecture Notes in Computer Science, ISBN 9783642161070, Volume 6331

Known algorithms for learning PDFA can only be shown to run in time polynomial in the so-called distinguishability μ of the target machine, besides the number...

Computer Science | Artificial Intelligence (incl. Robotics) | Computation by Abstract Devices | Computers and Education | Algorithm Analysis and Problem Complexity | Logics and Meanings of Programs | Mathematical Logic and Formal Languages | Intel·ligència artificial | Aprenentatge automàtic | Probably approximately correct learning | PAC learning | Informàtica | Machine learning | PDFA | Àrees temàtiques de la UPC

Computer Science | Artificial Intelligence (incl. Robotics) | Computation by Abstract Devices | Computers and Education | Algorithm Analysis and Problem Complexity | Logics and Meanings of Programs | Mathematical Logic and Formal Languages | Intel·ligència artificial | Aprenentatge automàtic | Probably approximately correct learning | PAC learning | Informàtica | Machine learning | PDFA | Àrees temàtiques de la UPC

Book Chapter

2010, Lecture Notes in Computer Science, ISBN 9783642154874, Volume 6339

In this paper we extend the PAC learning algorithm due to Clark and Thollard for learning distributions generated by PDFA to automata whose transitions may...

Pattern Recognition | Computer Science | Image Processing and Computer Vision | Artificial Intelligence (incl. Robotics) | Computation by Abstract Devices | Algorithm Analysis and Problem Complexity | Mathematical Logic and Formal Languages | Intel·ligència artificial | Aprenentatge automàtic | Probably approximately correct learning | PAC learning | Informàtica | Machine learning | PDFA | Àrees temàtiques de la UPC

Pattern Recognition | Computer Science | Image Processing and Computer Vision | Artificial Intelligence (incl. Robotics) | Computation by Abstract Devices | Algorithm Analysis and Problem Complexity | Mathematical Logic and Formal Languages | Intel·ligència artificial | Aprenentatge automàtic | Probably approximately correct learning | PAC learning | Informàtica | Machine learning | PDFA | Àrees temàtiques de la UPC

Book Chapter

No results were found for your search.

Cannot display more than 1000 results, please narrow the terms of your search.