Filters








1,379 Hits in 2.9 sec

Page 6493 of Mathematical Reviews Vol. , Issue 89K [page]

1989 Mathematical Reviews  
Stoer (D-WRZB-A) 89k:90169 90C35 90C30 Zenios, Stavros A. (1-PAWH-DS); Mulvey, John M. (1-PRIN-C) Vectorization and multitasking of nonlinear network programming algorithms. Math.  ...  (I-CLBR-SS) Numerical comparisons of nonlinear programming algorithms on serial and vector processors using automatic differentiation. Math. Programming 42 (1988), no. 2 (Ser. B), 375-389.  ... 

Page 5852 of Mathematical Reviews Vol. , Issue 89J [page]

1989 Mathematical Reviews  
Summary: “The concept of multitasking mathematical programs is discussed, and an application of multitasking to the multiple- 909 ECONOMICS, OPERATIONS RESEARCH, PROGRAMMING, GAMES 5852 cost-row linear  ...  Summary (translated from the Russian): “We give criteria for optimality and suboptimality in a piecewise-linear problem on a network, where the nonlinearity is a result of applying the operation of taking  ... 

Multitask Learning Based on Least Squares Support Vector Regression for Stock Forecast

Heng-Chang Zhang, Qing Wu, Fei-Yan Li, Hong Li
2022 Axioms  
Based on this hypothesis, we propose a multitask learning least squares support vector regression (MTL-LS-SVR) algorithm, and an extension, EMTL-LS-SVR.  ...  A Krylov-Cholesky algorithm is introduced to determine the optimal solutions of the models.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/axioms11060292 fatcat:owxeawqcgzafxm7od2jxogpzz4

Multitask Learning with CTC and Segmental CRF for Speech Recognition [article]

Liang Lu, Lingpeng Kong, Chris Dyer, Noah A. Smith
2017 arXiv   pre-print
labels and durations, and the latter classifies each frame as either an output symbol or a "continuation" of the previous label.  ...  In this paper, we train a recognition model by optimizing an interpolation between the SCRF and CTC losses, where the same recurrent neural network (RNN) encoder is used for feature extraction for both  ...  RNN(·) denotes the nonlinear recurrence operation used in an RNN, which takes the previous hidden state and the feature vector at the current timestep as inputs, and produce an updated hidden state vector  ... 
arXiv:1702.06378v4 fatcat:52fnlhsfd5g4delr2guywny55e

Diff-DAC: Distributed Actor-Critic for Average Multitask Deep Reinforcement Learning [article]

Sergio Valcarcel Macua and Aleksi Tukiainen and Daniel García-Ocaña Hernández and David Baldazo and Enrique Munoz de Cote and Santiago Zazo
2020 arXiv   pre-print
We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named Diff-DAC, with application to single-task and to average multitask reinforcement learning (MRL).  ...  of a linear program.  ...  Acknowledgements We thank Haitham Bou-Ammar and Peter Vrancx for insightful discussions.  ... 
arXiv:1710.10363v6 fatcat:efo5frxuzncsfmnpkekz2d4f4m

Artificial Intelligence in Biological Activity Prediction [chapter]

João Correia, Tiago Resende, Delora Baptista, Miguel Rocha
2019 Advances in Intelligent Systems and Computing  
We discuss some of the most used compound featurization techniques and the major databases of chemical compounds relevant to these tasks.  ...  Numerous machine learning algorithms for activity prediction recently emerged, becoming an indispensable approach to mine chemical information from large compound datasets.  ...  Portuguese FCT under the scope of the strategic funding of UID/BIO/04469/2019 unit and BioTec-Norte operation (NORTE-01-0145-FEDER-000004) funded by the European Regional Development Fund under the scope  ... 
doi:10.1007/978-3-030-23873-5_20 fatcat:hrdvbvpiyzahjjnrwvedpaxfde

EchoFilter: End-to-End Neural Network for Acoustic Echo Cancellation [article]

Lu Ma, Song Yang, Yaguang Gong, Xintian Wang, Zhongqin Wu
2021 arXiv   pre-print
The network is trained using multitask learning by employing an auxiliary classification network for double-talk detection.  ...  periods in background noise and nonlinear distortion scenarios.  ...  To overcome this problem, numeric methods have been proposed, such as Nonlinear AEC (NLAEC) method by using a set of nonlinear basis functions for echo This work was supported by National Key R&D Program  ... 
arXiv:2105.14666v1 fatcat:vzaz347kejbk5ag63jlgqiqj5e

On Learning High Dimensional Structured Single Index Models [article]

Nikhil Rao, Ravi Ganti, Laura Balzano, Rebecca Willett, Robert Nowak
2016 arXiv   pre-print
Estimation in this context requires learning both the feature weights and the nonlinear function that relates features to observations.  ...  networks with significantly less computational cost.  ...  Finally, neural networks have emerged as a powerful alternative to learn nonlinear transfer functions that can be basically thought of being defined by compositions of nonlinear functions.  ... 
arXiv:1603.03980v2 fatcat:m2y6hz2ghbgjxlvf7ng3e5ma74

Table of Contents

2022 IEEE Transactions on Cybernetics  
Li 3867 Fixed-Time Fuzzy Control for a Class of Nonlinear Systems . . . . . . . . . . . . . .Y. Sun, F. Wang, Z. Liu, Y. Zhang, and C. L. P.  ...  Zhao 3971 Novel Multitask Conditional Neural-Network Surrogate Models for Expensive Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tcyb.2022.3173165 fatcat:hfg4tdb5d5fjrdvrzxkstwfq2a

Intelligent Modeling and Verification 2014

Guiming Luo, Xiaoyu Song, Xiaojing Yang, Krishnaiyan Thulasiraman
2014 Journal of Applied Mathematics  
A total of 16 papers describe optimal system modeling. They focus on system modeling, optimal filtering and scheduling, image modeling, pattern recognition, and network modeling.  ...  After the success of the previous special issue Intelligent Modeling and Verification, which was published last year, we are pleased to announce that the new special issue Intelligent Modeling and Verification  ...  In addition, we would like to express our appreciation for the editorial board members of this journal, who provided valuable help and support throughout the preparation of this special issue.  ... 
doi:10.1155/2014/632027 fatcat:qfrhxkghfnccrnjm5mqxygzcjy

Data Mining and Soft Computing using Support Vector Machine: A Survey

Subhankar Das, Sanjib Saha
2013 International Journal of Computer Applications  
It works better than KNN and nonlinear SVM. In future by extends this method, it will useful for variety of application domains such as climate modeling and dynamic network analysis.  ...  In soft computing, neural network is a type of network includes many simple processors and each processor should have small amount of local memory.  ... 
doi:10.5120/13554-1367 fatcat:qpwndgz4qbclflfz3oardksh74

A survey Paper on Feature Extraction and Classification in ECG Biometric Signal

Kalyani U. Girde, Asst. Prof. Nandini Dhole
2017 IJARCCE  
Weights are allocated to the features inside the kernel of each task. We break down the network comprising of all the feature weights into sparse and low rank components.  ...  In this paper, multitask learning approach is proposed in which highlight extraction and classifier configuration are completed all the while.  ...  The resulting convex algorithms keep the global solution properties of support vector machines.  ... 
doi:10.17148/ijarcce.2017.63123 fatcat:6igbreq6jnhubpo7qsx6fcujae

Advanced machine-learning techniques in drug discovery

Moe Elbadawi, Simon Gaisford, Abdul W. Basit
2020 Drug Discovery Today  
Such limitations include their need for big data, sparsity in data, and their lack of interpretability.  ...  In this review, we detail the use of advanced techniques to circumvent these challenges, with examples drawn from drug discovery and allied disciplines.  ...  Acknowledgements The authors thank the Engineering and Physical Sciences Research Council (EPSRC), UK for its financial support (EP/S009000/1).  ... 
doi:10.1016/j.drudis.2020.12.003 pmid:33290820 fatcat:es4pvfn6xjemnluslaowd3x75u

Engineering and Scientific Subroutine Library Release 3 for IBM ES/3090 vector multiprocessors [Technical note]

R. C. Agarwal, F. G. Gustavson, J. McComb, S. Schmidt
1989 IBM Systems Journal  
He has worked in the areas of nonlinear differential equa- tions, linear algebra, symbolic computation, computer-aided de- sign of networks, design and analysis of algorithms, and programming applications  ...  network analysis and design.  ... 
doi:10.1147/sj.282.0345 fatcat:e7aclq2b6zgdbmwohe223ed334

Advances in neural information processing systems 8: Proceedings of the 1995 conference

1997 Computers and Mathematics with Applications  
Constructive algorithms for hierarchical mixtures of experts (S.R. Waterhouse and A.J. Robinson). An information-theoretic learning algorithm for neural network classification (D. Miller, A. Rao, K.  ...  Optimal asset allocation using adaptive dynamic programming (R. Neuneier). Using the future to "sort out" the present: Rankprop and multitask learning for medical risk evaluation (it. Caruana, S.  ... 
doi:10.1016/s0898-1221(97)90029-8 fatcat:6b5tr2ej4vepdktke4h2n3szfy
« Previous Showing results 1 — 15 out of 1,379 results