Filters








6,850 Hits in 4.2 sec

Deep Transfer: A Markov Logic Approach

Jesse Davis, Pedro Domingos
2011 The AI Magazine  
Our algorithm discovers structural regularities in the source domain in the form of Markov logic formulas with predicate variables, and instantiates these formulas with predicates from the target domain  ...  Our approach has successfully transferred learned knowledge among molecular biology, Web and social network domains.  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily represent-Articles SPRING 2011 3 ing the official policies, either expressed or  ... 
doi:10.1609/aimag.v32i1.2330 fatcat:fe6nbklufbbmtjrvriad7w6qme

Deep transfer via second-order Markov logic

Jesse Davis, Pedro Domingos
2009 Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09  
Humans routinely perform deep transfer, but few learning systems, if any, are capable of it. In this paper we propose an approach based on a form of second-order Markov logic.  ...  Our algorithm discovers structural regularities in the source domain in the form of Markov logic formulas with predicate variables, and instantiates these formulas with predicates from the target domain  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ARO, DARPA  ... 
doi:10.1145/1553374.1553402 dblp:conf/icml/DavisD09 fatcat:47bijot2g5amtajp4wsb5q3vz4

Learning, Probability and Logic: Toward a Unified Approach for Content-Based Music Information Retrieval

Helene-Camille Crayencour, Carmine-Emanuele Cella
2019 Frontiers in Digital Humanities  
and (deep) learning.  ...  Traditional approaches have generally treated these two aspects separately, probability and learning being the usual way to represent uncertainty in knowledge, while logical representation being the usual  ...  variable discovery in statistical models and predicate invention in Inductive Logic Programming. • Deep transfer learning: Another direction of interest is deep transfer learning.  ... 
doi:10.3389/fdigh.2019.00006 fatcat:nsphz2frebgy5bhcybvpfcyfey

A Survey on Neural-symbolic Systems [article]

Dongran Yu, Bo Yang, Dayou Liu, Hui Wang
2021 arXiv   pre-print
In contrast, symbolic systems have exceptional cognitive intelligence through efficient reasoning, but their learning capabilities are poor.  ...  In this case, an ideal intelligent system--a neural-symbolic system--with high perceptual and cognitive intelligence through powerful learning and reasoning capabilities gains a growing interest in the  ...  The definition of Markov logic network is as follows [49] : Definition 2 Markov logic network is a set of pairs (F i , w i ), where F i is a formula in first-order logic, and w i represents weight of  ... 
arXiv:2111.08164v1 fatcat:bc33afiitnb73bmjtrfbdgkwpy

Natural Language Processing. A Machine Learning Perspective

Julia Ive
2021 Computational Linguistics  
Part III "Deep Learning" describes the basics of deep learning modelling for classification and structured prediction tasks. The part is finalised with the basics of sequence-tosequence modelling.  ...  This textbook introduces NLP from the ML standpoint elaborating on fundamental approaches and algorithms used in the field: such as statistical and deep learning models, generative and discriminative,  ...  The chapter also explains such transfer learning techniques as pre-training, multi-task learning, choice of parameters for sharing, etc.  ... 
doi:10.1162/coli_r_00423 fatcat:rbztldsm6bgjlemmajt7wvpb6y

A Probabilistic Approach to Knowledge Translation [article]

Shangpu Jiang, Daniel Lowd, Dejing Dou
2015 arXiv   pre-print
distributions, specially using Markov random fields and Markov logic networks.  ...  We refer to this task as "knowledge translation" (KT). Unlike data translation and transfer learning, KT does not require any data from the source or target schema.  ...  Structure Learning The structure of the target knowledge can also be learned via standard structure learning algorithms for Markov random fields or Markov logic networks.  ... 
arXiv:1507.03181v1 fatcat:7msy5ngi2jd4xgi4i74sljqwqu

Scalable Statistical Relational Learning for NLP

William Yang Wang, William Cohen
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts  
Abstract: Statistical Relational Learning (SRL) is an interdisciplinary research area that combines firstorder logic and machine learning methods for probabilistic inference.  ...  Prerequisites: No prior knowledge of statistical relational learning is required.  ...  "Markov logic networks."  ... 
doi:10.18653/v1/n16-4005 dblp:conf/naacl/WangC16 fatcat:u5gngszpyvfknfk46a4q7cdjm4

STATISTICAL RELATIONAL LEARNING: A STATE-OF-THE-ART REVIEW

Muhamet Kastrati, Marenglen Biba
2019 Journal of Engineering Technology and Applied Sciences  
Taskar et al. [71] extended Markov networks (MNs) into relational Markov networks (RMNs), and Domingos and Richardson [18] into Markov logic networks (MLNs).  ...  As shown in Figure 1 , SRL combines a logic-based representation with probabilistic modeling and machine learning.  ...  Markov logic networks MLNs [60] is a state-of-the-art SRL model that integrates FOL representation with MN modeling.  ... 
doi:10.30931/jetas.594586 fatcat:qoei3pteibd6la4oqin6rvrxqi

The structure of evolved representations across different substrates for artificial intelligence [article]

Arend Hintze, Douglas Kirkpatrick, Christoph Adami (Michigan State University)
2018 arXiv   pre-print
We show that information in Markov Brains is localized and sparsely distributed, while the other neural network substrates "smear" information about the environment across all nodes, which makes them vulnerable  ...  Here we compare how recurrent artificial neural networks, long short-term memory units, and Markov Brains sense and remember their environments.  ...  This material is based in part upon work supported by the National Science Foundation under Cooperative Agreement No. DBI-0939454.  ... 
arXiv:1804.01660v1 fatcat:x37kroqxzngzxnt6jp5iybgtfe

Transfer learning using computational intelligence: A survey

Jie Lu, Vahid Behbood, Peng Hao, Hua Zuo, Shan Xue, Guangquan Zhang
2015 Knowledge-Based Systems  
To improve the performance of existing transfer learning methods and handle the knowledge transfer process in real-world systems, computational intelligence has recently been applied in transfer learning  ...  This paper systematically examines computational intelligence-based transfer learning techniques and clusters related technique developments into four main categories: a) neural network-based transfer  ...  Acknowledgment The work presented in this paper was supported by the Australian Research Council (ARC) under discovery grant DP140101366.  ... 
doi:10.1016/j.knosys.2015.01.010 fatcat:vu2ttscic5fq3nm2tkdid4fs64

Incorporation of Deep Neural Network Reinforcement Learning with Domain Knowledge [article]

Aryan Karn, Ashutosh Acharya
2021 arXiv   pre-print
and Reinforcement Learning.  ...  On numerous such occasions, machine-based model development may profit essentially from the human information on the world encoded in an adequately exact structure.  ...  Weight-learning in turn returns as traditional, victimizing the structure.  ... 
arXiv:2107.14613v2 fatcat:cddkguo3gvcgxn6s67ca26ucii

DeepPSL: End-to-end perception and reasoning with applications to zero shot learning [article]

Nigel P. Duffy, Sai Akhil Puranam, Sridhar Dasaratha, Karmvir Singh Phogat, Sunil Reddy Tiyyagura
2021 arXiv   pre-print
PSL represents first-order logic in terms of a convex graphical model -- Hinge Loss Markov random fields (HL-MRFs).  ...  The key to our approach is to represent predicates in first-order logic using deep neural networks and then to approximately back-propagate through the HL-MRF and thus train every aspect of the first-order  ...  Disclaimer: The views reflected in this article are the views of the authors and do not necessarily reflect the views of the global EY organization or its member firms.  ... 
arXiv:2109.13662v3 fatcat:cgz6m554izfozijciy3jpc5c6e

Structured machine learning: the next ten years

Thomas G. Dietterich, Pedro Domingos, Lise Getoor, Stephen Muggleton, Prasad Tadepalli
2008 Machine Learning  
The field of inductive logic programming (ILP) has made steady progress, since the first ILP workshop in 1991, based on a balance of developments in theory, implementations and applications.  ...  More recently there has been an increased emphasis on Probabilistic ILP and the related fields of Statistical Relational Learning (SRL) and Structured Prediction.  ...  Vector Logic-based Approach," Grant Reference BB/E000940/1.  ... 
doi:10.1007/s10994-008-5079-1 fatcat:arzjk4d7wrgffnzt4znrsfrb5q

Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks [article]

Arindam Das, Saikat Roy, Ujjwal Bhattacharya, Swapan Kumar Parui
2018 arXiv   pre-print
In this work, a region-based Deep Convolutional Neural Network framework is proposed for document structure learning.  ...  Exploiting the nature of region based influence modelling, a secondary level of 'intra-domain' transfer learning is used for rapid training of deep learning models for image segments.  ...  Deep Convolutional Neural Network Architecure DCNNs are currently one of the most popular models for deep learning.  ... 
arXiv:1801.09321v3 fatcat:fd64qcf35janxkmraf7ckwt244

Markov Logic: An Interface Layer for Artificial Intelligence

Pedro Domingos, Daniel Lowd
2009 Synthesis Lectures on Artificial Intelligence and Machine Learning  
Markov logic is a powerful new language that accomplishes this by attaching weights to first-order formulas and treating them as templates for features of Markov random fields.  ...  ., the Internet in networking, the relational model in databases, etc.). So far this interface layer has been missing in AI.  ...  In this section, we describe two recent methods for deep transfer learning in relational domains using Markov logic.  ... 
doi:10.2200/s00206ed1v01y200907aim007 fatcat:em6ggc2ha5f4lgaie53jkdjtbu
« Previous Showing results 1 — 15 out of 6,850 results