994 Hits in 2.2 sec

Evolutionary Multitask Optimization: a Methodological Overview, Challenges and Future Research Directions [article]

Eneko Osaba, Aritz D. Martinez, Javier Del Ser
2021 arXiv   pre-print
Additionally, the emerging paradigm of Evolutionary Multitasking tackles multitask optimization scenarios by using as inspiration concepts drawn from Evolutionary Computation.  ...  The main purpose of this survey is to collect, organize and critically examine the abundant literature published so far in Evolutionary Multitasking, with an emphasis on the methodological patterns followed  ...  Furthermore, similar authors that proposed MFEA-II in 2019, introduced two years before a Linearized Domain Adaptation MFEA (LDA-MFEA) [21] .  ... 
arXiv:2102.02558v2 fatcat:3imaqbxisvaehobb3pyf2dbp7y

CIS Publication Spotlight [Publication Spotlight]

Haibo He, Jon Garibaldi, Kay Chen Tan, Julian Togelius, Yaochu Jin, Yew Soon Ong
2020 IEEE Computational Intelligence Magazine  
Evolutionary multitasking, or multifactorial optimization, is an emerging subfield of multitask optimi zation, which integrates evolutionary computation and multitask learning.  ...  In order to design a CNN with promising performance, extensive expertise in both CNNs and the investigated problem domain is required, which is not necessarily avail able to every interested user.  ... 
doi:10.1109/mci.2020.3019871 fatcat:icdr7pp7grbqhoxlzjlwps2ro4

muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems [article]

Andrea Gesmundo, Jeff Dean
2022 arXiv   pre-print
We define an evolutionary approach designed to jointly select the prior knowledge relevant for each task, choose the subset of the model parameters to train and dynamically auto-tune its hyperparameters  ...  The resulting system can leverage cross tasks knowledge transfer, while being immune from common drawbacks of multitask approaches such as catastrophic forgetting, gradients interference and negative transfer  ...  While, an increase in compute leads to a linear increase in exploration budget.  ... 
arXiv:2205.10937v2 fatcat:qy3wo5pvwnadzlz3vqapgzt7ne

Evolutionary Architecture Search For Deep Multitask Networks [article]

Jason Liang, Elliot Meyerson, Risto Miikkulainen
2018 arXiv   pre-print
The size and complexity of this problem exceeds human design ability, making it a compelling domain for evolutionary optimization.  ...  character recognition domain.  ...  Evolutionary methods have also had success in MTL, especially in sequential decision-making domains [ Figure 1 : Example soft ordering network with three shared layers.  ... 
arXiv:1803.03745v2 fatcat:pcjt222zbfesrlpiwwxd2go3qq

Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning [article]

Ying Bi, Bing Xue, Mengjie Zhang
2020 arXiv   pre-print
Experimental results show that the new approach outperforms these compared methods in almost all the comparisons.  ...  Using evolutionary computation algorithms to solve multiple tasks with knowledge sharing is a promising approach.  ...  The adaptive knowledge transfer is achieved by changing the crossover operators in MEFA using the information collected from the evolutionary process.  ... 
arXiv:2012.09444v2 fatcat:hkcij2mltnfa5cn2qzvyndfqpa

Table of contents

2021 IEEE Transactions on Cybernetics  
Kwong 2550 Toward Adaptive Knowledge Transfer in Multifactorial Evolutionary Computation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Yan 2663 Joint Learning of Multiple Latent Domains and Deep Representations for Domain Adaptation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tcyb.2021.3071166 fatcat:2rhnoufzxbeh3k7xhwyenvwwvu

AT-MFCGA: An Adaptive Transfer-guided Multifactorial Cellular Genetic Algorithm for Evolutionary Multitasking [article]

Eneko Osaba, Javier Del Ser, Aritz D. Martinez, Jesus L. Lobo, Francisco Herrera
2021 arXiv   pre-print
In this paper we introduce a novel adaptive metaheuristic algorithm to deal with Evolutionary Multitasking environments coined as Adaptive Transfer-guided Multifactorial Cellular Genetic Algorithm (AT-MFCGA  ...  Among the different approaches that can address this problem effectively, Evolutionary Multitasking resorts to concepts from Evolutionary Computation to solve multiple problems within a single search process  ...  In [48] , a solver referred to as self-regulated evolutionary multitasking optimization is presented.  ... 
arXiv:2010.03917v2 fatcat:vgp6vsjpzreb7hwxqxbtnnlfmi

Multi-Task Optimization and Multi-Task Evolutionary Computation in the Past Five Years: A Brief Review

Qingzheng Xu, Na Wang, Lei Wang, Wei Li, Qian Sun
2021 Mathematics  
Inspired by this concept, the paradigm of multi-task evolutionary computation (MTEC) has recently emerged as an effective means of facilitating implicit or explicit knowledge transfer across optimization  ...  in this fascinating territory.  ...  [20] , multitask optimization (MTO) [11] , multitasking [12] , evolutionary multitasking (EMT) [21] , evolutionary multitasking (EMT) [22] , and multifactorial operation optimization (MFOO) [23] .  ... 
doi:10.3390/math9080864 fatcat:nnkdm4zkwvaxveh5cvblhbk5ve

An Effective Variable Transformation Strategy in Multitasking Evolutionary Algorithms

Qingzheng Xu, Lei Wang, Jungang Yang, Na Wang, Rong Fei, Qian Sun
2020 Complexity  
Multitasking evolutionary algorithm (MTEA), which solves multiple optimization tasks simultaneously in a single run, has received considerable attention in the community of evolutionary computation, and  ...  Keeping this in mind, a multitasking evolutionary algorithm (named MTDE-VT) is realized as an instance by embedding the proposed variable transformation strategy into multitasking differential evolution  ...  Few works have been conducted in the literature for variable transformation in evolutionary multitasking.  ... 
doi:10.1155/2020/8815117 fatcat:losbzans5rfylectvjgjppbt2m

Leveraging Sequence Classification by Taxonomy-Based Multitask Learning [chapter]

Christian Widmer, Jose Leiva, Yasemin Altun, Gunnar Rätsch
2010 Lecture Notes in Computer Science  
We treat each organism as one task and present three novel multitask learning methods to handle situations in which the relationships among tasks can be described by a hierarchy or by a graph.  ...  Multitask learning, a machine learning technique that recently received considerable attention, considers the problem of learning across tasks that are related to each other.  ...  Acknowledgments We would like to thank Sören Sonnenburg for help with the implementation of algorithms presented in this work.  ... 
doi:10.1007/978-3-642-12683-3_34 fatcat:6bko4pwfobb4fo4bte46gu64ka

A Survey of Transfer and Multitask Learning in Bioinformatics

Qian Xu, Qiang Yang
2011 Journal of Computing Science and Engineering  
Transfer and multitask learning offer an attractive alternative, by allowing useful knowledge to be extracted and transferred from data in auxiliary domains helps counter the lack of data problem in the  ...  In this article, we survey recent advances in transfer and multitask learning for bioinformatics applications.  ...  Multitask learning stresses generating benefits for learning performance improvements in all related domains.  ... 
doi:10.5626/jcse.2011.5.3.257 fatcat:oruxwutza5godismndbqad2lm4

A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking

Xiaoliang Ma, Qunjian Chen, Yanan Yu, Yiwen Sun, Lijia Ma, Zexuan Zhu
2020 Frontiers in Neuroscience  
The well-known multifactorial evolutionary algorithm (MFEA) has been successfully introduced to solve MTO problems based on transfer learning.  ...  However, it uses a simple and random inter-task transfer learning strategy, thereby resulting in slow convergence.  ...  Bali et al. (2017) put forward a linearized domain adaptation strategy to deal with the issue of the negative knowledge transfer between uncorrelated tasks.  ... 
doi:10.3389/fnins.2019.01408 pmid:31992969 pmcid:PMC6971124 fatcat:hp3fwedowba3thjmx3t3yxxuza

Inferring latent task structure for Multitask Learning by Multiple Kernel Learning

Christian Widmer, Nora C Toussaint, Yasemin Altun, Gunnar Rätsch
2010 BMC Bioinformatics  
If data is available for several different but related problem domains, Multitask Learning algorithms can be used to learn a model based on all available information.  ...  In Bioinformatics, many problems can be cast into the Multitask Learning scenario by incorporating data from several organisms.  ...  There has been previous work using Domain Adaptation (closely related to Multitask Learning) in the context of splice site prediction [3] .  ... 
doi:10.1186/1471-2105-11-s8-s5 pmid:21034430 pmcid:PMC2966292 fatcat:43h5vn5bizafldf6irpzicx6fi

Evolutionary Neural AutoML for Deep Learning [article]

Jason Liang, Elliot Meyerson, Babak Hodjat, Dan Fink, Karl Mutch, and Risto Miikkulainen
2019 arXiv   pre-print
Deep neural networks (DNNs) have produced state-of-the-art results in many benchmarks and problem domains.  ...  LEAF makes use of both state-of-the-art evolutionary algorithms (EAs) and distributed computing frameworks.  ...  ACKNOWLEDGEMENTS Thanks to Joseph Sirosh and Justin Ormont for inspiring discussions and feedback in the course of this research, and in particular to Joseph for suggestions on minimization and hyperparameter  ... 
arXiv:1902.06827v3 fatcat:aojhwsjd5ner7c43hojv5isj3i

Half a Dozen Real-World Applications of Evolutionary Multitasking, and More [article]

Abhishek Gupta, Lei Zhou, Yew-Soon Ong, Zefeng Chen, Yaqing Hou
2022 arXiv   pre-print
domains.  ...  The concept of evolutionary multitasking (EMT) fills this gap. It unlocks a population's implicit parallelism to jointly solve a set of tasks, hence creating avenues for skills transfer between them.  ...  CONCLUSIONS Evolutionary multitasking (EMT) is an emerging paradigm for jointly solving multiple tasks in a single optimization run.  ... 
arXiv:2109.13101v4 fatcat:dz2xepsivnberh2ga7d4xw7xqu
« Previous Showing results 1 — 15 out of 994 results