Filters








63,537 Hits in 1.6 sec

Automated Relational Meta-learning [article]

Huaxiu Yao, Xian Wu, Zhiqiang Tao, Yaliang Li, Bolin Ding, Ruirui Li, Zhenhui Li
2020 arXiv   pre-print
In this paper, motivated by the way of knowledge organization in knowledge bases, we propose an automated relational meta-learning (ARML) framework that automatically extracts the cross-task relations  ...  In addition, current task-specific meta-learning methods may either suffer from hand-crafted structure design or lack the capability to capture complex relations between tasks.  ...  AUTOMATED META-KNOWLEDGE GRAPH CONSTRUCTION AND UTILIZATION In this section, we first discuss how to organize and distill knowledge from historical learning process and then expound how to leverage such  ... 
arXiv:2001.00745v1 fatcat:ky673vwxsjfgrftut3aqwvyphy

Proposal for the 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR) [chapter]

Joeran Beel, Lars Kotthoff
2019 Lecture Notes in Computer Science  
and meta-learning community.  ...  Especially through meta-learning, impressive performance improvements have been achieved.  ...  meta learning in IR applications. • Familiarize the IR community with algorithm selection and meta-learning tools and research that has been published in related disciplines such as machine learning. •  ... 
doi:10.1007/978-3-030-15719-7_53 fatcat:tvb7mwtvz5cyhmhdjbadruqmtm

Presentation of a simple machine learning framework for semi-automated screening in systematic review or meta-analysis of aging and longevity research studies

Marko Lalović
2021 Zenodo  
Presentation slides of a research project to develop a machine learning framework to semi-automate citation screening in systematic reviews and meta-analyses.  ...  Outline: Background Related Work Our Contribution Methods Results  ...  To date, no use of any tools related to automating (or semi-automating) the screening process of systematic reviews or meta-analyses of aging and longevity research was reported.  ... 
doi:10.5281/zenodo.4594866 fatcat:42okvz2hsvehpdhxswoodnihfq

Presentation of a simple machine learning framework for semi-automated screening in systematic review or meta-analysis of aging and longevity research studies

Marko Lalović
2021 Zenodo  
Presentation slides of a research project to develop a machine learning framework to semi-automate citation screening in systematic reviews and meta-analyses.  ...  Outline: Background Related Work Our Contribution Methods Results  ...  To date, no use of any tools related to automating (or semi-automating) the screening process of systematic reviews or meta-analyses of aging and longevity research was reported.  ... 
doi:10.5281/zenodo.4594311 fatcat:664ztckacrbqzoztzg43lezz4m

Towards Automated Semi-Supervised Learning

Yu-Feng Li, Hai Wang, Tong Wei, Wei-Wei Tu
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose to present an automated learning system for SSL (AUTO-SSL).  ...  First, meta-learning with enhanced meta-features is employed to quickly suggest some instantiations of the SSL techniques which are likely to perform quite well.  ...  We first consider meta-learning that transforms automated SSL as a supervised learning and then exact appropriate features for data sets by not only traditional meta-features but also unsupervised learning  ... 
doi:10.1609/aaai.v33i01.33014237 fatcat:tzbjoucnjnfw5pv3xiat2vvk4q

Auto-Meta: Automated Gradient Based Meta Learner Search [article]

Jaehong Kim, Sangyeul Lee, Sungwan Kim, Moonsu Cha, Jung Kwon Lee, Youngduck Choi, Yongseok Choi, Dong-Yeon Cho, Jiwon Kim
2018 arXiv   pre-print
In this paper, we verify that automated architecture search synergizes with the effect of gradient-based meta learning.  ...  Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered  ...  Related Works Meta-learning Meta learning as a theme is quite general, and extends well beyond the gradient based meta learners for few shot classification tasks.  ... 
arXiv:1806.06927v2 fatcat:uqn2tsabd5gsbm42l7p5c2hm54

Automated Planning for Personalised Course Composition

Antonio Garrido, Eva Onaindia, Oscar Sapena
2009 2009 Ninth IEEE International Conference on Advanced Learning Technologies  
We present a LOM-compliant learning approach that uses an automated planning process to create personalised learning courses while giving special attention to the development of reusable learning objects  ...  These facilities are essential to develop automated decision processes for providing course compositions tailored to the specific characteristics of each individual learner.  ...  the basis for common automated learning activities.  ... 
doi:10.1109/icalt.2009.39 dblp:conf/icalt/GarridoOS09 fatcat:tf5rbgaw2nfgbn3ivsci3wfghu

Automated Machine Learning, Bounded Rationality, and Rational Metareasoning [article]

Eyke Hüllermeier and Felix Mohr and Alexander Tornede and Marcel Wever
2021 arXiv   pre-print
In this paper, we will look at automated machine learning (AutoML) and related problems from the perspective of bounded rationality, essentially viewing an AutoML tool as an agent that has to train a model  ...  on a given set of data, and the search for a good way of doing so (a suitable "ML pipeline") as deliberation on a meta-level.  ...  More specifically, we will look at automated machine learning and related problems from the perspective of bounded rationality, essentially viewing an AutoML tool as an agent that has to train a model  ... 
arXiv:2109.04744v1 fatcat:7pjkv5uc25dn5pchtxz55sll3m

Presentation slides for: "A Simple Machine Learning Framework for Citation Screening of Aging and Longevity Research Studies"

Marko Lalović
2021 Zenodo  
Presentation slides of a research project to develop a machine learning framework to semi-automate citation screening in systematic reviews and meta-analyses.  ...  Outline: Background Related Work Our Contribution Methods Results  ...  To date, no use of any tools related to automating (or semi-automating) the screening process of systematic reviews or meta-analyses of aging and longevity research was reported.  ... 
doi:10.5281/zenodo.4603371 fatcat:lq2m2ctvwbh27eo6z7yr2mugxi

Influence of meta-information on decision-making: Lessons learned from four case studies

Maria Riveiro, Tove Helldin, Goran Falkman
2014 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA)  
We summarize the results of these four case studies and discuss lessons learned for the design of future computerized support systems regarding the visualization of meta-information.  ...  Section II provides a brief review of related works, mainly covering the areas of meta-information visualization.  ...  Most of the research discussions of meta-information relate to the effects of uncertainty visualization on decision-making [6] .  ... 
doi:10.1109/cogsima.2014.6816534 dblp:conf/cogsima/RiveiroHF14 fatcat:drdstgmm7zag7p2mznso2thlru

Editorial for the Special Issue on Automated Design and Assessment of Heuristic Search Methods

Gabriela Ochoa, Mike Preuss, Thomas Bartz-Beielstein, Marc Schoenauer
2012 Evolutionary Computation  
Machine learning, meta-modelling and multilevel search approaches can and have been applied to automate these three processes.  ...  intelligence, optimization, statistics and machine learning.  ...  Machine learning, meta-modelling and multilevel search approaches can and have been applied to automate these three processes.  ... 
doi:10.1162/evco_e_00071 pmid:22564097 fatcat:juvsbpsfbfc57acobg7ujmau2y

Automated Machine Learning – a brief review at the end of the early years [article]

Hugo Jair Escalante
2020 arXiv   pre-print
Automated machine learning (AutoML) is the sub-field of machine learning that aims at automating, to some extend, all stages of the design of a machine learning system.  ...  In the context of supervised learning, AutoML is concerned with feature extraction, pre processing, model design and post processing.  ...  This waive also witnessed the resurgence of meta-learning as a critical step towards automating the selection of classification models.  ... 
arXiv:2008.08516v3 fatcat:xygxkejxvvd5joz2nouxya5ska

Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles [article]

Fei Ye, Pin Wang, Ching-Yao Chan, Jiucai Zhang
2020 arXiv   pre-print
Recent advances in supervised learning and reinforcement learning have provided new opportunities to apply related methodologies to automated driving.  ...  In this paper, we thus propose a meta reinforcement learning (MRL) method to improve the agent's generalization capabilities to make automated lane-changing maneuvers at different traffic environments,  ...  Meta learning, or learning to learn, refers to the methods can enable agents adapt quickly to new tasks using the prior knowledge or inductive biases learned from the previously seen related tasks.  ... 
arXiv:2008.12451v1 fatcat:vx7d7pwn3vhjlbcnactnbxwdqq

Meta learning Framework for Automated Driving [article]

Ahmad El Sallab, Mahmoud Saeed, Omar Abdel Tawab, Mohammed Abdou
2017 arXiv   pre-print
In this paper we propose a Meta learning framework, based on data set aggregation, to improve generalization of imitation learning algorithms.  ...  The success of automated driving deployment is highly depending on the ability to develop an efficient and safe driving policy.  ...  Meta Learning Framework for Automated Driving In this section the Meta Learning framework is presented F igure 1.  ... 
arXiv:1706.04038v1 fatcat:eqgqmntxrzepjp3veo5ba4jhzu

Recommender system for model driven software development

Stefan Kögel
2017 Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering - ESEC/FSE 2017  
We found 4374 meta models with 17249 versions. 244 of these meta models were changed at least ten times and are candidates for learning common model transformations.  ...  Further information can be taken from instance-to meta-model relationships, modeling related artifacts (e.g. correctness constraints), and versions histories of models under version control.  ...  Based on our data sets of models and their meta data (from A1 and A2) we plan to apply machine learning techniques and heuristic search algorithms similar to [20] in order to learn common model transformations  ... 
doi:10.1145/3106237.3119874 dblp:conf/sigsoft/Kogel17 fatcat:xofsv2ugvjcwzatvprk5dut7xe
« Previous Showing results 1 — 15 out of 63,537 results