Filters








81 Hits in 3.5 sec

Prolog Technology Reinforcement Learning Prover [chapter]

Zsolt Zombori, Josef Urban, Chad E. Brown
2020 Lecture Notes in Computer Science  
The core of the toolkit is a compact and easy to extend Prolog-based automated theorem prover called plCoP. plCoP builds on the leanCoP Prolog implementation and adds learning-guided Monte-Carlo Tree Search  ...  We present a reinforcement learning toolkit for experiments with guiding automated theorem proving in the connection calculus.  ...  We provide an open-source Prolog implementation of rlCoP, called plCoP, that uses the SWI-Prolog [40] environment. 2. We extend the guidance of leanCoP to reduction steps involving unification. 3.  ... 
doi:10.1007/978-3-030-51054-1_33 fatcat:e6ilb5wlcne65e2y4qoesydizy

Prolog Technology Reinforcement Learning Prover [article]

Zsolt Zombori, Josef Urban, Chad E. Brown
2020 arXiv   pre-print
The core of the toolkit is a compact and easy to extend Prolog-based automated theorem prover called plCoP. plCoP builds on the leanCoP Prolog implementation and adds learning-guided Monte-Carlo Tree Search  ...  We present a reinforcement learning toolkit for experiments with guiding automated theorem proving in the connection calculus.  ...  Prolog Technology Reinforcement Learning Prover The toolkit is available at our repository. 4 Its core is our plCoP connection prover based on the leanCoP implementation and inspired by rlCoP. leanCoP  ... 
arXiv:2004.06997v1 fatcat:mbymzgsnvrczzgpjxt7rgejvua

Automated Deduction: Looking Ahead

Donald W. Loveland
1999 The AI Magazine  
The inference engine of the logic programming language Prolog is a resolution system.  ...  Specific industries do learn through meetings, trade papers, and the like that particular problems can be addressed with the new technology.  ... 
doi:10.1609/aimag.v20i1.1442 dblp:journals/aim/Loveland99 fatcat:quvjcbyot5fzfga27lzwp6pqwa

Towards Finding Longer Proofs [article]

Zsolt Zombori, Adrián Csiszárik, Henryk Michalewski, Cezary Kaliszyk, Josef Urban
2021 arXiv   pre-print
We present a reinforcement learning (RL) based guidance system for automated theorem proving geared towards Finding Longer Proofs (FLoP).  ...  On these benchmarks, FLoP is competitive with strong theorem provers despite using very limited search, due to its ability to solve problems that are prohibitively long for other systems.  ...  Machine learning systems for guiding theorem provers. A large body of research exists that aims to provide guidance for theorem provers via machine learning.  ... 
arXiv:1905.13100v2 fatcat:ynksh52rrrc2hjuywsnr7pbtam

Logic-Based Technologies for Intelligent Systems: State of the Art and Perspectives

Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini
2020 Information  
Along this line, this paper provides an overview of logic-based approaches and technologies by sketching their evolution and pointing out their main application areas.  ...  Future perspectives for exploitation of logic-based technologies are discussed as well, in order to identify those research fields that deserve more attention, considering the areas that already exploit  ...  neural networks, genetic fuzzy systems, rough fuzzy hybridization, and Reinforcement Learning with fuzzy, neural, or evolutionary methods as well as symbolic reasoning methods.  ... 
doi:10.3390/info11030167 fatcat:e3wed54dyzabldrnml7khx37te

Learning Ex Nihilo [article]

Selmer Bringsjord, Naveen Sundar Govindarajulu
2019 arXiv   pre-print
Learning ex nihilo is an agent's learning "from nothing," by the suitable employment of schemata for deductive and inductive reasoning.  ...  Such integration will require, among other things, the symbiotic interoperation of state-of-the-art automated reasoners and high-expressivity planners, with statistical/connectionist ML technology.  ...  Office of Naval Research to invent, formalize, and implement new forms of learning based on automated reasoning.  ... 
arXiv:1903.03515v2 fatcat:vxyzvgfdure2ddte6vtsp4tbnq

Introduction to the 30th International Conference on Logic Programming Special Issue

MICHAEL LEUSCHEL, TOM SCHRIJVERS
2014 Theory and Practice of Logic Programming  
Inspired by reinforcement learning, our technique propagates positive rewards to random variable/outcome pairs used in a consistent sample.  ...  A prototype of the integrated system is implemented in XSB Prolog. Customisable Handling of Java References in Prolog Programs Sergio Castro, Kim Mens and Paulo Moura.  ... 
doi:10.1017/s1471068414000581 fatcat:6fczd6mhxjcutozkk6t23lvn5e

Logic and Learning (Dagstuhl Seminar 19361)

Michael Benedikt, Kristian Kersting, Phokion G. Kolaitis, Daniel Neider, Michael Wagner
2020 Dagstuhl Reports  
The goal of building truly intelligent systems has forever been a central problem in computer science.  ...  capabilities traditionally developed in the logic and automated reasoning communities in order to achieve the next step towards building intelligent systems, including making progress at the frontier  ...  There is a growing need to enable the disparate communities of logic and learning to interact with each other, and we noted from the seminar that researchers from each community appreciated the perspective  ... 
doi:10.4230/dagrep.9.9.1 dblp:journals/dagstuhl-reports/BenediktKKN19 fatcat:rwjks5mydzhctlvedtel3vtzoy

Logic-based technologies for multi-agent systems: a systematic literature review

Roberta Calegari, Giovanni Ciatto, Viviana Mascardi, Andrea Omicini
2020 Autonomous Agents and Multi-Agent Systems  
On the other hand, agents and multi-agent systems (MAS) have been at the core of the design of intelligent systems since their very beginning, and their long-term connection with logic-based technologies  ...  , which characterised their early days, might open new ways to engineer explainable intelligent systems.  ...  Technological notes: The DALI technology consists of a Prolog system for SICStus Prolog (no specific version is indicated), and lays unmaintained on GitHub.  ... 
doi:10.1007/s10458-020-09478-3 fatcat:4s2rhluwijan3abqq7dl2htiv4

Automated Theorem Proving in GeoGebra: Current Achievements

Francisco Botana, Markus Hohenwarter, Predrag Janičić, Zoltán Kovács, Ivan Petrović, Tomás Recio, Simon Weitzhofer
2015 Journal of automated reasoning  
mature stage, we embarked on a project of incorporating and testing a number of dierent automated provers for geometry in GeoGebra.  ...  Since including automated deduction tools in GeoGebra could bring a whole new range of teaching and learning scenarios, and since automated theorem proving and discovery in geometry has reached a rather  ...  An early example (from the late 70's) is Geom, a Prolog-based geometry theorem-prover ( [Coelho & al., 1986] ).  ... 
doi:10.1007/s10817-015-9326-4 fatcat:rh7lvmmy75eipaqmkvf3dqxs3a

The future of urban models in the Big Data and AI era: a bibliometric analysis (2000-2019) [article]

Marion Maisonobe
2019 arXiv   pre-print
We consider two areas in urban research: one, covering the academic research dealing with transportation systems and the other, with water systems.  ...  OR "Random Forest$" OR "Genetic Algorithm$" OR "Bayes* Network$" OR "belief network$" OR "directed acyclic graphic*" OR "supervised learn*" OR "semi$supervised learn*" OR "unsupervised learn*" OR "reinforcement  ...  In a report, McKinsey analysts consequently distinguish between "artificial narrow AI" -potential applications of AI in business and the public sector (i.e. transfer learning, reinforcement learning and  ... 
arXiv:1912.00532v1 fatcat:rxkfrmii2rdttaglqc63yhyjvu

Artificial Intelligence Modelling: Data Driven and Theory Driven Approaches [chapter]

Klaus Manhart
1996 Social Science Microsimulation  
AI or knowledge based systems can be used in the social sciences for both theory driven and data driven model building.  ...  A Prolog program was written that firstly represents the essential concepts of the theory in the architecture of an expert system.  ...  For example, converting verbal model descriptions into symbolic terms is far from easy in general.  ... 
doi:10.1007/978-3-662-03261-9_19 fatcat:iszdebgbfncvlpjb3ypytxtufy

Inductive logic programming at 30: a new introduction [article]

Andrew Cropper, Sebastijan Dumančić
2022 arXiv   pre-print
We introduce the necessary logical notation and the main learning settings; describe the building blocks of an ILP system; compare several systems on several dimensions; describe four systems (Aleph, TILDE  ...  Inductive logic programming (ILP) is a form of machine learning. The goal of ILP is to induce a hypothesis (a set of logical rules) that generalises training examples.  ...  ., ) , in which an ILP system interactively learns a search query from examples, and software specification recovery from execution behaviour (Cohen, b, a) . ) combine LFIT with a reinforcement learning  ... 
arXiv:2008.07912v5 fatcat:omhppz2oxjgpbghvwul3iqsa2q

Inductive Logic Programming At 30: A New Introduction

Andrew Cropper, Sebastijan Dumančić
2022 The Journal of Artificial Intelligence Research  
We introduce the necessary logical notation and the main learning settings; describe the building blocks of an ILP system; compare several systems on several dimensions; describe four systems (Aleph, TILDE  ...  Inductive logic programming (ILP) is a form of machine learning. The goal of ILP is to induce a hypothesis (a set of logical rules) that generalises training examples.  ...  • We define the standard ILP learning settings (Section 3). • We describe the basic assumptions required to build an ILP system (Section 4). • We compare many ILP systems and describe the features they  ... 
doi:10.1613/jair.1.13507 fatcat:5fdf7gspgbckzldtp5wyomb6wq

Advancements in Microprocessor Architecture for Ubiquitous AI—An Overview on History, Evolution, and Upcoming Challenges in AI Implementation

Fatima Hameed Khan, Muhammad Adeel Pasha, Shahid Masud
2021 Micromachines  
Artificial intelligence (AI) has successfully made its way into contemporary industrial sectors such as automobiles, defense, industrial automation 4.0, healthcare technologies, agriculture, and many other  ...  However, this capability requires processing huge amounts of learning data to extract useful information in real time.  ...  The situation was worsened by the AI symbolic languages LISP and Prolog, as they led to integration issues in complex systems.  ... 
doi:10.3390/mi12060665 fatcat:edbpii37wfgnxamx76k42qldsq
« Previous Showing results 1 — 15 out of 81 results