Documents about Neural Information Processing Systems
proposal
University of Illinois, Urbana Champaign, CS 446
Excerpt: ... estions: 1. How to apply BP to different problems? 2. Why can BP achieve impressive results? 3. What's the cons of BP? So I plan to do a deep survey on this topic. The following papers will be referenced: References [1] J. Yedidia, W. Freeman, and Y. Weiss. Understanding Belief Propagation and its Generalizations. In IJCAI 2001 Distinguished Lecture track. [2] B. Frey and D. Mackay. A Revolution: Belief Propagation in Graphs with Cycles. In M. Jordan, M. Kearns and S. Solla, (Eds.) Adv. in Neural Information Processing Systems , Volumn 10. MIT Press, 1998. [3] K. Murphy, Y. Weiss, and M. Jordan. Loopy Belief Propagation for Approximate Inference: an Empirical Study. In Proc. Uncertainty in AI, 1999. [4] P. Felzenszwalb and D. Huttenlocher. Efficient Belief Propagation for Early Vision. In IEEE Conference on Computer Vision and Pattern Recognition, 2004. [5] N. Petrovic, I. Cohen, B. Frey, R. Koetter, and T. Huang. Enforcing Integrability for Surface Reconstruction Algorithms Using Belief Propagation in Graphic ...
|
|
proposal
University of Illinois, Urbana Champaign, CS 446
Excerpt: ... estions: 1. How to apply BP to different problems? 2. Why can BP achieve impressive results? 3. What's the cons of BP? So I plan to do a deep survey on this topic. The following papers will be referenced: References [1] J. Yedidia, W. Freeman, and Y. Weiss. Understanding Belief Propagation and its Generalizations. In IJCAI 2001 Distinguished Lecture track. [2] B. Frey and D. Mackay. A Revolution: Belief Propagation in Graphs with Cycles. In M. Jordan, M. Kearns and S. Solla, (Eds.) Adv. in Neural Information Processing Systems , Volumn 10. MIT Press, 1998. [3] K. Murphy, Y. Weiss, and M. Jordan. Loopy Belief Propagation for Approximate Inference: an Empirical Study. In Proc. Uncertainty in AI, 1999. [4] P. Felzenszwalb and D. Huttenlocher. Efficient Belief Propagation for Early Vision. In IEEE Conference on Computer Vision and Pattern Recognition, 2004. [5] N. Petrovic, I. Cohen, B. Frey, R. Koetter, and T. Huang. Enforcing Integrability for Surface Reconstruction Algorithms Using Belief Propagation in Graphic ...
|
|
ee645.19
University of Hawaii - Hilo, EE 645
Excerpt: ... conditional independence assumption works reasonably well. Nave Bayes has been applied to many pattern recognition problems including text classification problems. Logistic Regression Let P(D=1| X=x) = 1/(1+exp(s) where s=wTx +w0 Then negative log likelihood function given by -l(x) = log (P(D= -1|X=x)/P(D=1|X=x) = s Logistic regression is a linear classifier where if s0 decide D= -1 and otherwise decide D=1. Common assumption is that likelihood functions are Gaussian vectors. Key is to learn weight vector based on training examples. Use log-likelihood energy function plus regularization and train using gradient descent. Comparison between Nave Bayes and Logistic Regression A. Ng and M. Jordan, `On Discriminative vs. Generative Classifiers: A comparison of Logistic Regression and Nave Bayes' Neural Information Processing Systems , 2002. Nave Bayes converges in O(log(n) updates, but asymptotic error more than Logistic Regression Logistic regression converges in O(n) updates On tests of both algorit ...
|
|
ee645.18
University of Hawaii - Hilo, EE 645
Excerpt: ... escent. Comparison between Nave Bayes and Logistic Regression A. Ng and M. Jordan, `On Discriminative vs. Generative Classifiers: A comparison of Logistic Regression and Nave Bayes Neural Information Processing Systems , 2002. Also http:/www.cs.cmu.edu/%7Etom/NewChapters.html Nave Bayes converges in O(log(n) updates, but asymptotic error more than Logistic Regression Logistic regression converges in O(n) updates On tests of both algorithms common feature was for small number of examples Nave Bayes better, but for large number of examples Logistic Regression better. ...
|
|
cs4811-ch11-neural-nets-1
Mich Tech, CS 4811
Excerpt: ... y used structure in machine learning. The input has to be numeric. They are useful when the learned function is not easily understood (compare to decision trees which implement a DNF Boolean formula) . p.29/30 Final remarks (contd) Typical examples are: handwritten character recognition (ZIP code), speech recognition, learning to pronounce written text. Designing and training neural networks is still an art requiring experience and experiments conference: Neural Information Processing Systems (NIPS) yearly publication of best results: Advances in Neural Information Processing Systems . p.30/30 ...
|
|
lecture15
Princeton, COS 513
Excerpt: ... ocess given at Figure 3 steps of the EM algorithm are E step M step where N (t+1) T zn zn |x n=1 z|x 1 N = n=1 E E [zn |xn ]T xn which resembles the normal equations. R EFERENCES [1] H. Hotelling, Analysis of a Complex of Statistical Variables into Principal Components, J. Educational Psychology, vol. 24, pp. 417441, 1933. [2] K. Pearson, On lines and planes of closest t to systems of points in space, Philosophical Magazine, vol. 2, no. 6, pp. 559572, 1901. [3] C. M. Bishop and C. K. I. Williams, Em optimization of latent-variable density models, in Advances in Neural Information Processing Systems 8, pp. 465471, MIT Press, 1996. ...
|
|
0002901
Berkeley, ICIP 2006
Excerpt: ... t improvements in terms of AP are obtained. After the MIL training, we expect the learned model is more pure. We mean the positive model has less affection from the negative instances in the positive bags. So we [2] J. Ramon & L. D. Raedt, Multi instance neural network, Proc. of workshop at ICML00 on Attribute-Value and Relational Learning: Crossing the boundaries, 2000. [3] M. Naphade, et al., A light scale concept ontology for multimedia understanding for TRECVID 2005, IBM Research Report RC23612 (W0505-104), May, 2005. [4] M. Naphade & J.R. Smith, A generalized multiple instance learning algorithm for large scale modeling of multimedia semantics, Proc. of ICASSP05. [5] O. Maron & A. L. Ratan, Multiple-instance learning for natural scene classification, ICML98. [6] O. Maron & T. Lozano-Perez, A framework for multiple instance learning, Neural Information Processing Systems , 1998. [7] Q. Zhang, et al., Content-based image retrieval using multiple instance learnin ...
|
|
Readme
Wisconsin, ECE 539
Excerpt: ... Notes . The entire package is put into the file cascor1.c . twospirals and cascor are two executable program compiled for HP9000. do NOT download to other machines! . all three files ended with extension "net" are data files. . "howto compil ...
|
|
BrunoClassRefs
Berkeley, VS 298
Excerpt: ... in a spiking network. Advances in Neural Information Processing Systems , 18, MIT press Berridge M.J. 1998. Neuronal calcium signalling, Neuron, 21, 1, 13-26 Berridge M.J. 2002. The endoplasmic reticulum: a multifunctional signaling organelle, Cell Calcium, 32 235-249 Bootman M.D., Lipp P. & Berridge M.J. 2001. The organisation and function of local Ca2+ signals, J. Cell Science, 114, 2213-2222 Canolty R. et al. 2006. Science, accepted (probably available from rcanolty@gmail.com) Conway F. & Siegelman J. 2004. Dark hero of the information age: in search of Norbert Wiener, the father of cybernetics, Basic Books Dan Y. & Poo M-M. 2006. Spike Timing-Dependent Plasticity: from synapse to perception, Physiol. Rev. 86, 1033-1048 Freeman W.J. 2005. A field-theoretic approach to understanding scale-free neocortical dynamics, Biol. Cybern. Freeman W.J. et al. 2006. Fine spatio-temporal structure of phase in human intracranial EEG, Clin. Neurophysiol. 117, 6, 1228-43 Fries P. 2005. A mechanism for cognitive dynamics: ...
|
|
BrunoClassRefs
Berkeley, VS 298
Excerpt: ... ity in a spiking network. Advances in Neural Information Processing Systems , 18, MIT press Berridge M.J. 1998. Neuronal calcium signalling, Neuron, 21, 1, 13-26 Berridge M.J. 2002. The endoplasmic reticulum: a multifunctional signaling organelle, Cell Calcium, 32 235-249 Bootman M.D., Lipp P. & Berridge M.J. 2001. The organisation and function of local Ca2+ signals, J. Cell Science, 114, 2213-2222 Canolty R. et al. 2006. Science, accepted (probably available from rcanolty@gmail.com) Conway F. & Siegelman J. 2004. Dark hero of the information age: in search of Norbert Wiener, the father of cybernetics, Basic Books Dan Y. & Poo M-M. 2006. Spike Timing-Dependent Plasticity: from synapse to perception, Physiol. Rev. 86, 1033-1048 Freeman W.J. 2005. A field-theoretic approach to understanding scale-free neocortical dynamics, Biol. Cybern. Freeman W.J. et al. 2006. Fine spatio-temporal structure of phase in human intracranial EEG, Clin. Neurophysiol. 117, 6, 1228-43 Fries P. 2005. A mechanism for cognitive dynami ...
|
|
lecture15
Berkeley, CS 294
Excerpt: ... arada and Stuart Russell (1999). Policy invariance under reward transformations: Theory and application to reward shaping. Proceedings of the 16th International Conference on Machine Learning. [3] Ng, Andrew Y. and Michael I. Jordan (2000). PEGASUS: A policy search method for large MDPs and POMDPs. Proceedings of the Sixteenth Conference on Uncertainty in Articial Intelligence. [4] Ng, Andrew Y., H. Jin Kim, Michael I. Jordan and Shankar Sastry (2003). Autonomous helicopter ight via Reinforcement Learning. Advances in Neural Information Processing Systems , vol. 16. [5] Ng, Andrew Y., Adam Coates, Mark Diel, Varun Ganapathi, Jamie Schulte, Ben Tse, Eric Berger and Eric Liang (2004). Autonomous inverted helicopter ight via reinforcement learning. International Symposium on Experimental Robotics. [6] Williams, Ronald J. (1992). Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning, vol. 8, p. 229-256. 4 ...
|
|
Sourav_Compressed
UMBC, CSEE 601
Excerpt: ... writing Recognition Natural Language Processing Biological Sequence Processing and so on . What makes this problem interesting? Given the structure, the parameters can be learned using standard techniques (e.g., Maximum Likelihood Estimation). Learning the structure is much harder. Inducing Probabilistic Grammars by Bayesian Model Merging p. 4/1 Solutions Proposed Earlier Successive State Splitting (HMMs) 1. Bell, Timothy C., John G. Cleary, Ian H. Whitten. Text Compression. Englewood Cliffs, N.J., Prentice Hall, 1990. 2. Ron, Dana, Yoram Singer, Naftali Tishbi. The power of amnesia. Advances of Neural Information Processing Systems , 6, Morgan Kauffman, San Mateo, CA, 1994. Stochastic Context Free Grammars 1. Cook, Craig M., Azriel Rosenfeld, Alan R. Aronson. Grammatical inference by hill climbing. Information Sciences, volume 10, pages 59 80, 1976. Inducing Probabilistic Grammars by Bayesian Model Merging p. 5/1 Bayesian Model Merging A model building process that learns the structure. Tw ...
|
|
CaseStudy_Aguilar
USF, JCARLSO 1
Excerpt: ... as well as the best regression-based method of data analysis (Stepwise Regression) Future Work Further refinements to data set may be useful Platform testing to reduce training time Testing on other data sets to provide additional evidence of effectiveness Automatic selection of number of neurons Improved error handling for system References [1] Consumer Information, California Air Resources Board Official Website, http:/www. arb.ca.gov/, May 7, 2003 [2] R. Yelkur, "Radial Basis Function Network for Predicting The Impact of Trip Reduction Strategies," Thesis report, April 1999 [3] R. Perez, "Artificial Neural Networks," University of South Florida Lecture Notes, Spring 2002 [4] A. Blum, R.L. Rivest, "Training a 3-node neural network is np-complete," Advances in Neural Information Processing Systems I, pp. 494-501, San Mateo, California, 1989 [5] P. van der Smagt, G. Hirzinger, "Why feed-forward networks are in a bad shape," Proceedings of the 8th International Conference on Artificial Neural Networks (IC ...
|
|
dynamicNets08-4up
Allan Hancock College, CS 9444
Excerpt: ... Dynamic Nets Cascade-Correlation Aims Reference to consider the concept of dynamic nets to look briefly at the cascade-correlation architecture/algorithm Fahlman, S. and Lebiere, C.: The Cascade-Correlation Learning Architecture, in Advances in Neural Information Processing Systems 2, D. S. Touretzky (ed.), Morgan Kaufmann Publishers, Los Altos CA, pp. 524-532. You can get a copy of this at http:/www.cse.unsw.edu.au/~billw/cs9444/fahlman91cascadecorrelation.pdf and you can find the code at http:/www.cse.unsw.edu.au/~billw/cs9444/cascor/cascor-v1.2.shar cascade, correlation dynamic nets problems with backprop cascade-correlation 1 Introduction Standard feedforward networks are static, in the sense that the number of units is fixed, along with the locations of connections between units (though not the weight values) As biological brains grow, at least, new neurons do get added (and axons grow and create synapses with the dendrites of other neurons). New synaptic connections grow e ...
|
|
DelormeMakeigIEEE2003
UCSD, SCCN 2003
Excerpt: ... r helpful discussion and suggestions. REFERENCES [1] [2] [3] [4] J. R. Wolpaw, D. J. McFarland, G. W. Neat, and C. A. Forneris, "An EEG-based brain-computer interface for cursor control," Electroencephalogr Clin Neurophysiol, vol. 78, pp. 252-9, 1991. D. J. McFarland, L. M. McCane, S. V. David, and J. R. Wolpaw, "Spatial filter selection for EEG-based communication," Electroencephalogr Clin Neurophysiol, vol. 103, pp. 386-94, 1997. D. J. McFarland and J. R. Wolpaw, "EEG-based communication and control: speed-accuracy relashionships," Applied Psychophysiology and Biofeedback, vol. in press, 2002. S. Makeig, A. J. Bell, T. P. Jung, and T. J. Sejnowski, "Independent component analysis of electroencephalographic data," in Advances in Neural Information Processing Systems 8, M. M. Touretzky D, Hasselmo M, Ed. Cambridge, MA: MIT Press, 1996, pp. 145-151. S. Makeig, S. Enghoff, T. P. Jung, and T. J. Sejnowski, "A natural basis for efficient brain-actuated control," IEEE Trans Rehabil Eng, vol. 8, pp. 208-11, 2000. ...
|
|
b-NIPS2003-2
UCSD, PROJECT 1
Excerpt: ... Submitted: Advances in Neural Information Processing Systems 2003. Towards social robots: Automatic evaluation of human-robot interaction by face detection and expression classication G. Littlewort , M.S. Bartlett , I. Fasel , J. Chenu , T. Kanda , H. Ishiguro , and J.R. Movellan Institute for Neural Computation, University of California, San Diego Intelligent Robotics and Communication Laboratory, ATR, Kyoto Japan. Email: gwen, marni, ian, joel, javier @inc.ucsd.edu 1 Introduction Computer animated agents and robots bring a social dimension to human computer interaction and force us to think in new ways about how computers could be used in daily life. Face to face communication is a real-time process operating at a time scale of less than a second. Thus fullling the idea of machines that interact face to face with us requires development of robust real-time perceptive primitives. In this paper we present rst steps towards the development of one suc ...
|
|
Presentation_Joshua_Menke
BYU, WORKSHOP 04
Excerpt: ... ences [1] L. Breiman. Bagging predictors. Machine Learning., 24(2):123140, 1996. [2] Rich Caruana, Shumeet Baluja, and Tom Mitchell. Using the future to "sort out" the present: Rankprop and multitask learning for medical risk evaluation. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems , volume 8, pages 959965, Cambridge, MA, 1996. The MIT Press. [3] Mark Craven and Jude W. Shavlik. Learning symbolic rules using artificial neural networks. In Paul E. Utgoff, editor, Proceedings of the Tenth International Conference on Machine Learning, pages 7380, San Mateo, CA, 1993. Morgan Kaufmann. BYU CS 24 [4] Mark W. Craven and Jude W. Shavlik. Extracting tree-structured representations of trained networks. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems , volume 8, pages 2430, Cambridge, MA, 1996. The MIT Press. [5] Pedro Domingos. Knowledge acquisition from exampl ...
|
|
pakdd07b
Concordia Chicago, BLF 0218
Excerpt: ... cular Invariant Clustering. IEEE Transactions on PAMI, Vol. 27, No. 12 (2005) 1856-1865 8. Wang, L., Bo, L.F., Jiao, L.C.: A modified K-Means clustering with a density-sensitive distance metric. RSKT 2006, Lecture Notes in Computer Science, Vol. 4062. SpringerVerlag, Berlin Heidelberg New York (2006) 544-551 9. Bousquet, O., Chapelle,O., Hein, M.: Measure based regularization. Advances in Neural Information Processing Systems 16 (NIPS), MIT Press, Cambridge, MA (2004) 10. Blum, A., Chawla, S.: Learning from labeled and unlabeled data using graph mincuts. Proceedings of the Eighteenth International Conference on Machine Learning (ICML) 18, (2001) 19-26 11. Syswerda, G.: Uniform crossover in genetic algorithms. In: Proceedings of the Third International Conference on Genetic Algorithms. Morgan Kaufmann Publishers, San Francisco, CA (1989) 2-9 12. Whitley, D.: A genetic algorithm tutorial. Statistics and Computing, Vol. 4 (1994) 65-85 13. Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Le ...
|
|
7-0-HierBys-DirProc
University of Illinois, Urbana Champaign, CS 446
Excerpt: ... y to see the forest while he's describing tree leaves Tell me about what you think the forest is / might be / should be CS446Fall '06 2 Bayesian Learning Next (future) Programming Assignment Not assigned yet Compare nave Bayes and logistic regression as examples of generative and discriminative classifiers A new text chapter available from Mitchell: Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression http:/www.cs.cmu.edu/%7Etom/NewChapters.html or navigate down from http:/www.cs.cmu.edu/~tom/ A classic paper: A. Y. Ng and M. Jordan. On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes. In Proceeding of Fourteenth Neural Information Processing Systems , 2002. Bayesian Learning CS446Fall '06 3 Jordan's Abstract Much research in statistics and machine learning is concerned with controlling some form of tradeoff between flexibility and variability. In the Bayesian approach, such control is often exerted via hierarchi ...
|
|
GNG
Harvey Mudd College, CS 152
Excerpt: ... elevant l amiammma ~alt tel al, lunLi taUlalllim all: III1~1111111 i !_m]m_m_m .:.: i!ii! !ii!i!' i!iiiiiii .: .:.:-.;: ~!iL!:ii~;ii!ii4i~q~:;i: Sources Baraldi and Blonda. A Survey of Fuzzy Clustering Algorithms for Pattern RecognitionPart II. IEEE Transactions on Systems, Man, and Cybernetics, 1999. Fritzke. A Growing Neural Gas Network Learns Topologies. Advances in Neural Information Processing Systems , 1994. Fritzke. A self organizing network that can follow non-stationary distributions. Proceedings of ICANN, 1997. Martinetz and Schulten. A Neural-Gas Network Learns Topologies. Articial Neural Networks, 1991. Rehtanz. and Leder. Stability Assessment of Electric Power Systems using Growing Neural Gas and Self-Organizing Maps. ESANN2000 Procedings, 2000. ...
|
|
42_Abstract
UCSD, CUNY 2007
Excerpt: ... ctic discontinuity. PhD Thesis, Stanford University. 2005. M. MacDonald, Probabilistic Constraints and Syntactic Ambiguity Resolution. LCP 9(2), 157-201, 1994. K. McRae, M. Spivey-Knowlton and M. Tanenhaus, Modeling the influence of thematic fit (and other constraints) in on-line sentence comprehension. JML, 38, pp. 283-312, 1998. S. Narayanan and D. Jurafsky, A Bayesian Model Predicts Human Parse Preference and Reading Time in Sentence Processing. In: Dietterich, Becker and Ghahramani, eds., Advances in Neural Information Processing Systems 14, MIT Press, 2002. U. Pado, M. Crocker and F. Keller, Modeling Semantic Role Plausibility in Human Sentence Processing. In: Proceedings of the Meeting of the European Chapter of the Association for Computational Linguistics, 2006. ...
|
|
a1
Georgia Tech, CS 7001
Excerpt: ... national Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), March 2007 Artificial Intelligence: International Joint Conference on Artificial Intelligence, January 2007 Cognitive Science: Cognitive Science Society Annual Meeting (CogSci), August 2007 Computational Science and Engineering: SIAM Annual Meeting, June 2007 Cryptography: CRYPTO, August 2007 Databases: ACM SIGMOD/PODS, June 2007 Graphics: ACM SIGGRAPH, August 2007 HCI: CHI, April 2007 Learning Science and Technology: International Conference of the Learning Sciences, June 2006 Machine Learning: Neural Information Processing Systems (NIPS), December 2006 Networking: Proceedings of ACM SIGCOMM, September 2007 Programming Languanges: ACM Programming Language Design and Implementation, June 2007 Robotics: Robotics Science and Systems, June 2007 Security: IEEE Symposium on Security and Privacy, May 2007 Software Engineering: ACM SIGSOFT Symposium on the Foundations of Software Enginee ...
|
|
Maus_pro
Wisconsin, ECE 539
Excerpt: ... se in time sensitive applications. References: 1. Principe, J. C. & Kuo, J.M. (1995). Dynamic modelling of chaotic time series with neural networks. Advances in Neural Information Processing Systems (Vol. 7, pp. 311318), MIT Press. 2. Smola, A. (1996) Regression Estimation with Support Vector Learning Machines, master's thesis, Technische Universitat Munchen, Munchen, Germany. * University of Wisconsin-Madison. Contact Email: amaus@wisc.edu ...
|