Filters








1,262 Hits in 4.2 sec

A Tutorial on Deep Neural Networks for Intelligent Systems [article]

Juan C. Cuevas-Tello and Manuel Valenzuela-Rendon and Juan A. Nolazco-Flores
2016 arXiv   pre-print
Deep Belief Networks (DBNs), which are used to build networks with more than two layers, are also described.  ...  Here, we present a tutorial of Deep Neural Networks (DNNs), and some insights about the origin of the term "deep"; references to deep learning are also given.  ...  We introduced Deep Neural Networks (DNNs) and Restricted Boltzmann Machines (RBMs), and their relationship to Deep Learning (DL) and Deep Belief Nets (DBNs).  ... 
arXiv:1603.07249v1 fatcat:cy36lfk2mzaqlbjq77uuho2eky

An extended BDI model for human behaviors: Decision-making, learning, interactions, and applications

Young-Jun Son, Sojung Kim, Hui Xi, Santosh Mungle
2013 2013 Winter Simulations Conference (WSC)  
The goal of this tutorial is to discuss an extended Belief-Desire-Intention (BDI) framework that the authors' research group has been developing last decade to meet such a challenge, integrating models  ...  Bayesian Belief Network, Decision Field Theory, Depth First Search) available in the fields of engineering, psychology, computational science, and statistics.  ...  ACKNOWLEDGMENTS The research works (methodologies and applications) discussed in this tutorial have been supported by the Air Force Office of Scientific Research under AFOSR/MURI F49620-03-1-0377 and FA9550  ... 
doi:10.1109/wsc.2013.6721437 dblp:conf/wsc/SonKXM13 fatcat:liqi4s64kbbipjejzx6ch3bms4

Modeling a Student's Behavior in a Tutorial-Like System Using Learning Automata

B.J. Oommen, M.K. Hashem
2010 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
This paper presents a new philosophy to model the behavior of a student in a tutorial-like system using learning automata (LAs).  ...  The model of the student in our system is inferred using a higher level LA, referred to as a meta-LA, which attempts to characterize the learning model of the students (or student simulators), while the  ...  Our belief is that these three families of algorithms represent three distinct types of learning paradigms and learning rates sufficient for the present research.  ... 
doi:10.1109/tsmcb.2009.2027220 pmid:19744915 fatcat:gzc4ny3hhbgo3e6jztssktu3de

Modeling a Student–Classroom Interaction in a Tutorial-Like System Using Learning Automata

B.J. Oommen, M.K. Hashem
2010 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
This paper presents a new philosophy to model the behavior of a student in a tutorial-like system using learning automata (LAs).  ...  The model of the student in our system is inferred using a higher level LA, referred to as a meta-LA, which attempts to characterize the learning model of the students (or student simulators), while the  ...  Our belief is that these three families of algorithms represent three distinct types of learning paradigms and learning rates sufficient for the present research.  ... 
doi:10.1109/tsmcb.2009.2032414 pmid:19884059 fatcat:ifes5ddjonci3me7ji6ow7ihiu

A Survey of Stochastic Simulation and Optimization Methods in Signal Processing

Marcelo Pereyra, Philip Schniter, Emilie Chouzenoux, Jean-Christophe Pesquet, Jean-Yves Tourneret, Alfred O. Hero, Steve McLaughlin
2016 IEEE Journal on Selected Topics in Signal Processing  
This survey paper offers an introduction to stochastic simulation and optimization methods in signal and image processing.  ...  It also discusses a range of optimization methods that have been adopted to solve stochastic problems, as well as stochastic methods for deterministic optimization.  ...  CONCLUSIONS AND OBSERVATIONS In writing this paper we have sought to provide an introduction to stochastic simulation and optimization methods in a tutorial format, but which also raised some interesting  ... 
doi:10.1109/jstsp.2015.2496908 fatcat:ldqpfq74tjgofewh6sx4zyqf44

Modeling language and cognition with deep unsupervised learning: a tutorial overview

Marco Zorzi, Alberto Testolin, Ivilin P. Stoianov
2013 Frontiers in Psychology  
DEEP BELIEF NETWORK Hierarchical generative model composed of a stack of RBMs, which can be greedily trained layer-wise in an unsupervised fashion.  ...  Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research.  ...  We then provided a step-by-step tutorial on how to practically perform a complete deep learning simulation, covering the main aspects related to the training, testing and analysis of deep belief networks  ... 
doi:10.3389/fpsyg.2013.00515 pmid:23970869 pmcid:PMC3747356 fatcat:hnszejz7yfeufgsdfbuxktplbe

Interactive Sensing and Decision Making in Social Networks

Vikram Krishnamurthy
2014 Foundations and Trends® in Signal Processing  
This monograph provides a survey, tutorial development, and discussion of four highly stylized examples: social learning for interactive sensing; tracking the degree distribution of social networks; sensing  ...  Despite being highly stylized, these examples provide a rich variety of models, algorithms and analysis tools that are readily accessible to a signal processing, control/systems theory, and applied mathematics  ...  An important associated problem discussed in Chapter 3 is how to actually construct random graphs via simulation algorithms.  ... 
doi:10.1561/2000000048 fatcat:5hr4ebohczhrlolw4whenlicj4

pyABC: Efficient and robust easy-to-use approximate Bayesian computation [article]

Yannik Schälte, Emmanuel Klinger, Emad Alamoudi, Jan Hasenauer
2022 arXiv   pre-print
At its core, it implements a sequential Monte-Carlo (SMC) scheme, with various algorithms to adapt to the problem structure and automatically tune hyperparameters.  ...  In particular, we implement algorithms to account for noise, to adaptively scale-normalize distance metrics, to robustly handle data outliers, to elucidate informative data points via regression models  ...  Acknowledgments We thank many collaboration partners and pyABC users for valuable input, in particular Frank Bergmann for the COPASI wrapper, and Elba Raimúndez for fruitful discussions.  ... 
arXiv:2203.13043v1 fatcat:ip35swrtbnepvjcnn7ymaxmava

Tutorial on Stochastic Optimization in Energy—Part I: Modeling and Policies

Warren B. Powell, Stephan Meisel
2016 IEEE Transactions on Power Systems  
Recognizing that we will never agree on a single notational system, this two-part tutorial proposes a simple, straightforward canonical model (that is most familiar to people with a control theory background  ...  He founded and directs CASTLE Labs (http://www.castlelab.princeton.edu), specializing in fundamental contributions to computational stochastic optimization with a wide range of applications. .  ...  ACKNOWLEDGMENT The authors would like to thank the careful reviews and helpful comments of the referees.  ... 
doi:10.1109/tpwrs.2015.2424974 fatcat:5igxvl6zv5fktdnrcdsw73gxz4

Agent-based simulation tutorial - simulation of emergent behavior and differences between agent-based simulation and discrete-event simulation

Wai Kin Victor Chan, Young-Jun Son, Charles M. Macal
2010 Proceedings of the 2010 Winter Simulation Conference  
This tutorial demonstrates the use of agent-based simulation (ABS) in modeling emergent behaviors.  ...  We illustrate agent-based modeling issues and simulation of emergent behaviors by using examples in social networks, auction-type markets, emergency evacuation, crowd behavior under normal situations,  ...  INTRODUCTION Agent-based simulation (ABS) is a rather new approach for simulating systems with interacting autonomous agents.  ... 
doi:10.1109/wsc.2010.5679168 dblp:conf/wsc/ChanSM10 fatcat:byjrvpuuanexpfjganwdvtyd7u

Book reports

2002 Computers and Mathematics with Applications  
A tutorial introduction. 1.1. Data representation and similarity. 1.2. A simple pattern recognition algorithm. 1.3. Some insights from statistical learning theory. 1.4. Hyperplane classifiers. 1.5.  ...  Network models. 7.1. Introduction. 7.2. Firing-rate models. 7.3. Feedforward networks. 7.4. Recurrent networks. 7.5. Excitatory- inhibitory networks. 7.6. Stochastic networks. 7.7.  ... 
doi:10.1016/s0898-1221(02)00272-9 fatcat:dlkuzp6p5nbilivckq5ezj5cbe

RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems [article]

Martin Mladenov, Chih-Wei Hsu, Vihan Jain, Eugene Ie, Christopher Colby, Nicolas Mayoraz, Hubert Pham, Dustin Tran, Ivan Vendrov, Craig Boutilier
2021 arXiv   pre-print
To address this, we develop RecSim NG, a probabilistic platform for the simulation of multi-agent recommender systems.  ...  and tracing; and a TensorFlow-based runtime for running simulations on accelerated hardware.  ...  Based on this embedding and user engagement, the recommender uses a deep network to learn a belief state (or estimate of the user latent state) ℎ ; it also learns a similar item representation.  ... 
arXiv:2103.08057v1 fatcat:wgg3hbvk5nee5fjliwz24rctbm

Unit commitment considering multiple charging and discharging scenarios of plug-in electric vehicles

Zhile Yang, Kang Li, Qun Niu, Aoife Foley
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
neural simulations: when do we need to start caring for networks, rather than about them?  ...  Brain- Computer Inter- faces tut4a: Tutorial 4(a): Robust Model-based Learning: Meth- ods, Algorithms and Applications tut4b: Tutorial 4(b):Simulating an entire ner- vous system?  ... 
doi:10.1109/ijcnn.2015.7280446 dblp:conf/ijcnn/YangLNF15 fatcat:6xlakikcfzfyhhm2spooe2j7ra

A Comparative Tutorial of Bayesian Sequential Design and Reinforcement Learning [article]

Mauricio Tec and Yunshan Duan and Peter Müller
2022 arXiv   pre-print
Reinforcement Learning (RL) is a computational approach to reward-driven learning in sequential decision problems.  ...  Rather than a comprehensive survey, the focus of the discussion is on solutions using standard tools for these two relatively simple sequential stopping problems.  ...  A neural network is used to represent Q(•). Let φ (k) denote the parameters of the neural network at iteration k.  ... 
arXiv:2205.04023v1 fatcat:olx7q6cqwncinhfvhkukmzkhie

A tutorial on Bayesian models of perception

Benjamin T. Vincent
2015 Journal of Mathematical Psychology  
This tutorial provides an introduction to core concepts in Bayesian modelling and should help a wide variety of readers to more deeply understand, or to generate their own Bayesian models of perception  ...  Core theoretical and implementational issues are covered, using the 2 alternativeforced-choice task as a case study.  ...  Acknowledgements I am grateful to Daniel Baker, Shane Lindsey, Keith May, Tom Wallis, Britt Anderson, Alastair Clarke, Anuenue Baker-Kukona, Ben Tatler, Kirsty Miller, and Karl Smith-Byrne for providing  ... 
doi:10.1016/j.jmp.2015.02.001 fatcat:h7ebwa6dlngbbi4fqbwzymbqoe
« Previous Showing results 1 — 15 out of 1,262 results