16,090 Hits in 2.7 sec

Neural Program Meta-Induction [article]

Jacob Devlin, Rudy Bunel, Rishabh Singh, Matthew Hausknecht, Pushmeet Kohli
2017 arXiv   pre-print
Most recently proposed methods for Neural Program Induction work under the assumption of having a large set of input/output (I/O) examples for learning any underlying input-output mapping.  ...  For intermediate data sizes, we demonstrate that the combined method of adapted meta program induction has the strongest performance.  ...  Conclusions In this work, we have contrasted two techniques for using cross-task knowledge sharing to improve neural program induction, which are referred to as adapted program induction and meta program  ... 
arXiv:1710.04157v1 fatcat:lawozjeljjgxnmarhguiwwcw2y

Abductive Knowledge Induction From Raw Data [article]

Wang-Zhou Dai, Stephen H. Muggleton
2021 arXiv   pre-print
In this paper, we present Abductive Meta-Interpretive Learning (Meta_Abd) that unites abduction and induction to learn neural networks and induce logic theories jointly from raw data.  ...  Experimental results demonstrate that Meta_Abd not only outperforms the compared systems in predictive accuracy and data efficiency but also induces logic programs that can be re-used as background knowledge  ...  In this paper, we integrate neural networks with Inductive Logic Programming (ILP) [Muggleton and de Raedt, 1994 ] to enable first-order logic theory induction from raw data.  ... 
arXiv:2010.03514v2 fatcat:6mtsp6ucvnafnme47sama6vuru

Approaches and Applications of Inductive Programming (Dagstuhl Seminar 17382)

Ute Schmid, Stephen H. Muggleton, Rishabh Singh, Marc Herbstritt
2018 Dagstuhl Reports  
This report documents the program and the outcomes of Dagstuhl Seminar 17382 "Approaches and Applications of Inductive Programming".  ...  After a short introduction to the state of the art to inductive programming research, an overview of the introductory tutorials, the talks, program demonstrations, and the outcomes of discussion groups  ...  Neural Program Meta-Induction. NIPS 2017: 2077-2085 Patrice Godefroid, Hila Peleg, Rishabh Singh. Learn & Fuzz: machine learning for input fuzzing. ASE 2017: 50-59 Sahil Bhatia, Rishabh Singh.  ... 
doi:10.4230/dagrep.7.9.86 dblp:journals/dagstuhl-reports/SchmidMS17 fatcat:dn76mje45bhqrnevejun4qp3ku

Genetic Algorithms with DNN-Based Trainable Crossover as an Example of Partial Specialization of General Search [chapter]

Alexey Potapov, Sergey Rodionov
2017 Lecture Notes in Computer Science  
Universal induction relies on some general search procedure that is doomed to be inefficient.  ...  We perform a feasibility study of this idea implementing such an operator in the form of a deep feedforward neural network.  ...  Thus, more technically related works are the works on meta-learning in neural networks.  ... 
doi:10.1007/978-3-319-63703-7_10 fatcat:4phoxn6a4bgr3ekbkhwv4bsdju

Inductive logic programming at 30 [article]

Andrew Cropper, Sebastijan Dumančić, Richard Evans, Stephen H. Muggleton
2021 arXiv   pre-print
Inductive logic programming (ILP) is a form of logic-based machine learning. The goal is to induce a hypothesis (a logic program) that generalises given training examples.  ...  We focus on (i) new meta-level search methods, (ii) techniques for learning recursive programs, (iii) new approaches for predicate invention, and (iv) the use of different technologies.  ...  As with the ability to learn recursive programs, the main development is to take a global view of the induction task by using meta-level search techniques.  ... 
arXiv:2102.10556v2 fatcat:kv7ktjbajng6jjfae3sq3ubbmu

Guest editors introduction: special issue on Inductive Logic Programming (ILP 2012)

Fabrizio Riguzzi, Filip Železný
2013 Machine Learning  
challenging applications (here, object recognition), augmenting its logical foundations (metainterpretative learning, interpretation dynamics), and combined with extra-logical machinelearning techniques (neural  ...  We are grateful to the authors, the reviewers, and to the publisher Springer for giving us the opportunity to compile this reflection of current research in inductive logic programming.  ...  Meta-interpretive learning is implemented with two different declarative representations: Prolog and Answer Set Programming. In the paper "Learning from Interpretation Transition" by K. Inoue, T.  ... 
doi:10.1007/s10994-013-5398-8 fatcat:4wi34sppyvdfdbiqlf2np32hvu

Inductive Transfer [chapter]

Ricardo Vilalta, Christophe Giraud-Carrier, Pavel Brazdil, Carlos Soares
2017 Encyclopedia of Machine Learning and Data Mining  
Here we describe some of them under the names of inductive transfer, transfer learning, multitask learning, meta-searching, meta-generalization, and domain adaptation.  ...  In the Inductive Logic Programming (ILP) setting this is referred to as predicate invention (Stahl (1995) []). [], Meta-Searching for Problem Solvers.  ...  Hence, inductive transfer studies how to improve learning by detecting, extracting, and exploiting (meta)knowledge in the form of invariant transformations across tasks.  ... 
doi:10.1007/978-1-4899-7687-1_138 fatcat:ptfmvvzd45ddzeecizv3y2pspm

Contrasting meta-learning and hyper-heuristic research: the role of evolutionary algorithms

Gisele L. Pappa, Gabriela Ochoa, Matthew R. Hyde, Alex A. Freitas, John Woodward, Jerry Swan
2013 Genetic Programming and Evolvable Machines  
The fields of machine meta-learning and hyper-heuristic optimisation have developed mostly independently of each other, although evolutionary algorithms (particularly genetic programming) have recently  ...  ) different communities of meta-learning and hyper-heuristic researchers.  ...  grammar-based genetic programming algorithm to evolve rule induction algorithms.  ... 
doi:10.1007/s10710-013-9186-9 fatcat:rxkljeappbea5m6bjmwahuqf24

Creating Rule Ensembles from Automatically-Evolved Rule Induction Algorithms [chapter]

Gisele L. Pappa, Alex A. Freitas
2010 Studies in Computational Intelligence  
First, an evolutionary algorithm (more precisely, a genetic programming algorithm) is used to automatically create complete rule induction algorithms.  ...  Secondly, the automatically-evolved rule induction algorithms are used to produce rule sets that are then combined into an ensemble.  ...  First, an evolutionary algorithm (a genetic programming algorithm) is used to automatically create complete rule induction algorithms.  ... 
doi:10.1007/978-3-642-05177-7_13 fatcat:fnbia2z6x5hzfnjuvk473lpf6u

Approaches and Applications of Inductive Programming (Dagstuhl Seminar 19202)

Luc De Raedt, Richard Evans, Stephen H. Muggleton, Ute Schmid, Michael Wagner
2019 Dagstuhl Reports  
In this report the program and the outcomes of Dagstuhl Seminar 19202 "Approaches and Applications of Inductive Programming" is documented.  ...  After a short introduction to the state of the art to inductive programming research, an overview of the introductory tutorials, the talks, program demonstrations, and the outcomes of discussion groups  ...  Related work on this approach includes: LIME, LRP (Layerwise Relevance Propagation),, prototype-based neural network layers: 01214, neural stethoscopes:  ... 
doi:10.4230/dagrep.9.5.58 dblp:journals/dagstuhl-reports/RaedtEMS19 fatcat:exhpnjoh2rcjre76eqlmpmcb4q

The foundation of efficient robot learning

Leslie Pack Kaelbling
2020 Science  
The RL2 algorithm (11) uses DRL in the factory to learn a general small program that runs in the wild but does not necessarily have the form of a machine-learning program.  ...  Inductive bias, in general, increases sample efficiency and generalizability.  ... 
doi:10.1126/science.aaz7597 pmid:32820109 fatcat:3sriq3u3kzd2jkuj4dgzb3jv4y

Accuracy of Machine Learning Algorithms for the Diagnosis of Autism Spectrum Disorder: Systematic Review and Meta-Analysis of Brain Magnetic Resonance Imaging Studies

Sun Jae Moon, Jinseub Hwang, Rajesh Kana, John Torous, Jung Won Kim
2019 JMIR Mental Health  
A functional magnetic resonance imaging/deep neural network subgroup meta-analysis (5 samples with 1345 participants) showed a sensitivity of 0.69 (95% CI 0.62-0.75), specificity of 0.66 (95% CI 0.61-0.70  ...  Results A total of 43 studies were included for the final analysis, of which a meta-analysis was performed on 40 studies (53 samples with 12,128 participants).  ...  Stacked-generalization* OR gradient-boosting-machine* OR gradient-boosted-regression-tree* OR random-forest* OR support-vector* OR Fuzzy* OR Markov* OR case-based-reasoning* OR simulated-annealing* OR inductive-logical-program  ... 
doi:10.2196/14108 pmid:31562756 pmcid:PMC6942187 fatcat:lphcfmt7lffcbkaxjg3h5dj2qy

Learning Compositional Rules via Neural Program Synthesis [article]

Maxwell I. Nye, Armando Solar-Lezama, Joshua B. Tenenbaum, Brenden M. Lake
2020 arXiv   pre-print
Instead of directly predicting outputs from inputs, we train our model to induce the explicit system of rules governing a set of previously seen examples, drawing upon techniques from the neural program  ...  Our rule-synthesis approach outperforms neural meta-learning techniques in three domains: an artificial instruction-learning domain used to evaluate human learning, the SCAN challenge datasets, and learning  ...  We additionally thank Tuan Anh Le for assistance using the pyprob probabilistic programming library. M. Nye is supported by an NSF Graduate Fellowship and an MIT BCS Hilibrand Graduate Fellowship.  ... 
arXiv:2003.05562v2 fatcat:ksgb2kd5rvfirnis7l5i3652o4

Synaptic and Axonal Plasticity Induction in the Human Cerebral Cortex [chapter]

Yoshikazu Ugawa
2015 Innovative Medicine  
It is again compatible with plasticity induction in animals.  ...  This chapter summarizes a newly developed method (quadripulse stimulation (QPS)) to induce neural plasticity in the human brain. What Is QPS?  ...  In contrast, pramipexole did not affect QPS effects Neural Plasticity Induction in the Human Cerebral Cortex 302 Fig. 9 9 Protocol for the meta-plasticity experimentsFig. 10 Time courses of QPS 1.5,  ... 
doi:10.1007/978-4-431-55651-0_24 fatcat:7rme2ygjhvhojfhsxf2u3oel2q

Book announcements

1993 Discrete Applied Mathematics  
Chapter 13: Relations, Functions, and Induction. Rela- tions. Functions. Sequences. Mathematical induction. Recurrence relations. Chapter 14: Graphs and Trees. Graphs.  ...  Chapter Guide Lines to VLSI Design of Neural Nets (IJ. Ramacher). ming and the theory of games. PART 4: NONLINEAR PROGRAMMING. Chapter 12: Nonlinear Programming.  ... 
doi:10.1016/0166-218x(93)90117-7 fatcat:mo4kjmd2czdg5hejcof7fmm6u4
« Previous Showing results 1 — 15 out of 16,090 results