Transfer Learning

Torrey, Lisa; Shavlik, Jude W.

doi:10.4018/978-1-60566-766-9.ch011

Cited by 1,486 publications

(879 citation statements)

References 0 publications

Supporting

Mentioning

760

Contrasting

Unclassified

Order By: Relevance

“…For such single and multiagent tasks, policy transfer is typically done within the same task domain for varying task complexity (Torrey and Shavlik, 2009) and less frequently between different task domains (Bou-Ammar et al, 2015). Recently, there has been work investigating the efficacy of using policy transfer in company with Evolutionary Algorithms (EAs) (Eiben and Smith, 2003) to boost evolved solution quality of evolved genotypes with various representations.…”

Section: Evolutionary Policy Transfermentioning

confidence: 99%

Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

Nitschke

Didi

2017

Front. Robot. AI

View full text Add to dashboard Cite

This study evaluates various evolutionary search methods to direct neural controller evolution in company with policy (behavior) transfer across increasingly complex collective robotic (RoboCup keep-away) tasks. Robot behaviors are first evolved in a source task and then transferred for further evolution to more complex target tasks. Evolutionary search methods tested include objective-based search (fitness function), behavioral and genotypic diversity maintenance, and hybrids of such diversity maintenance and objective-based search. Evolved behavior quality is evaluated according to effectiveness and efficiency. Effectiveness is the average task performance of transferred and evolved behaviors, where task performance is the average time the ball is controlled by a keeper team. Efficiency is the average number of generations taken for the fittest evolved behaviors to reach a minimum task performance threshold given policy transfer. Results indicate that policy transfer coupled with hybridized evolution (behavioral diversity maintenance and objective-based search) addresses the bootstrapping problem for increasingly complex keep-away tasks. That is, this hybrid method (coupled with policy transfer) evolves behaviors that could not otherwise be evolved. Also, this hybrid evolutionary search was demonstrated as consistently evolving topologically simple neural controllers that elicited high-quality behaviors.

show abstract

Section: Evolutionary Policy Transfermentioning

confidence: 99%

Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

Nitschke

Didi

2017

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…It has been empirically and theoretically shown that transfer learning can greatly improve the learning performance especially when only a small number of data are available in a target domain [3], [4]. Speech emotion recognition can benefit from using transfer learning as well.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, transfer learning has been proposed to develop methods to transfer useful information in one or more source tasks to a related target task [3]. It has been empirically and theoretically shown that transfer learning can greatly improve the learning performance especially when only a small number of data are available in a target domain [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition

Deng

Zhang

Marchi

et al. 2013

2013 Humaine Association Conference on Affective Computing and Intelligent Interaction

308

182

View full text Add to dashboard Cite

Abstract-In speech emotion recognition, training and test data used for system development usually tend to fit each other perfectly, but further 'similar' data may be available. Transfer learning helps to exploit such similar data for training despite the inherent dissimilarities in order to boost a recogniser's performance. In this context, this paper presents a sparse autoencoder method for feature transfer learning for speech emotion recognition. In our proposed method, a common emotion-specific mapping rule is learnt from a small set of labelled data in a target domain. Then, newly reconstructed data are obtained by applying this rule on the emotion-specific data in a different domain. The experimental results evaluated on six standard databases show that our approach significantly improves the performance relative to learning each source domain independently.

show abstract

“…The effectiveness of instance transfer depends on the relevance of the source domain to the target domain [19]. Since the distributions of the domains are usually unknown, the relevance can be estimated by the relevance of the source data to the target data.…”

Section: Introductionmentioning

confidence: 99%

Conformal decision-tree approach to instance transfer

Zhou

Smirnov

Schoenmakers

et al. 2017

Ann Math Artif Intell

View full text Add to dashboard Cite

Instance transfer for classification aims at boosting generalization performance of classification models for a target domain by exploiting data from a relevant source domain. Most of the instance-transfer approaches assume that the source data is relevant to the target data for the complete set of features used to represent the data. This assumption fails if the target data and source data are relevant only for strict subsets of the input features which we call "partially input-feature relevant". In this case these approaches may result in suboptimal classification models or even in a negative transfer. This paper proposes a new decision-tree approach to instance transfer when the source data are partially input-feature relevant to the target data. The approach selects input features for tree nodes using univariate transfer of source instances. The instance transfer is guided by a conformal test for source relevance estimation. Experimental results on real-world data sets demonstrate that the new decision-tree approach is capable of outperforming existing instance-transfer approaches, especially, when the source data are partially input-feature relevant to the target data.

show abstract

Transfer Learning

Cited by 1,486 publications

References 0 publications

Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition

Conformal decision-tree approach to instance transfer

Contact Info

Product

Resources

About