February 23, 2020

Neural Symbolic AI

Learning Algorithms via Neural Logic Networks

https://arxiv.org/abs/1904.01554

https://github.com/apayani?tab=repositories

Inductive Logic Programming via Differentiable Deep Neural Logic Networks

https://arxiv.org/pdf/1906.03523.pdf

https://github.com/apayani/ILP

Learning Explanatory Rules from Noisy Data

https://arxiv.org/pdf/1711.04574.pdf

https://github.com/ai-systems/DILP-Core Pytorch

Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and Reasoning

https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12345/12022

Learn To Explain Efficiently via Neural Logic Inductive Learning

https://openreview.net/attachment?id=SJlh8CEYDB&name=original_pdf

https://openreview.net/forum?id=SJlh8CEYDB

Code: https://github.com/gblackout/NLIL

DeepProbLog: Neural Probabilistic Logic Programming

http://papers.nips.cc/paper/7632-deepproblog-neural-probabilistic-logic-programming.pdf

code: https://bitbucket.org/problog/deepproblog/src/master/

Neural Logic Machines

https://arxiv.org/abs/1904.11694

https://github.com/google/neural-logic-machines

Logical Rule Induction and Theory Learning Using Neural Theorem Proving

https://arxiv.org/pdf/1809.02193.pdf

Code? https://github.com/ACampero/diff-Theory-ILP

Neural Theorem Provers Do Not Learn Rules Without Exploration

https://arxiv.org/pdf/1906.06805.pdf

https://github.com/Michiel29/ntp-release

RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools

https://arxiv.org/pdf/1909.07095.pdf

https://github.com/IBM/RuDaS

CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text

https://arxiv.org/pdf/1908.06177.pdf (надо дальше пройтись по ссылкам)

Bridging Machine Learning and Logical Reasoning by Abductive Learning

http://papers.nips.cc/paper/8548-bridging-machine-learning-and-logical-reasoning-by-abductive-learning.pdf

https://github.com/haldai/LogicalVision2

Using matrices to model symbolic relationships

http://papers.nips.cc/paper/3482-using-matrices-to-model-symbolic-relationship.pdf

Bridging Relational and Deep Learning

https://people.cs.kuleuven.be/~sebastijan.dumancic/RelationalDeepLearning/index.html

Learning Relational Representations with Auto-encoding Logic Programs

https://arxiv.org/pdf/1903.12577.pdf

Auto-encoding Logic Programs

https://sebdumancic.github.io/assets/pdf/2018/pubs/2018_DumancicGunsMeertBlockeel_NAMPI.pdf

Bias Specification Language

https://link.springer.com/referenceworkentry/10.1007%2F978-0-387-30164-8_73

Markov Logic Networks

https://homes.cs.washington.edu/~pedrod/papers/mlj05.pdf

code: https://alchemy.cs.washington.edu/

LEARNING INVARIANTS THROUGH SOFT UNIFICATION

https://arxiv.org/pdf/1909.07328.pdf

https://openreview.net/forum?id=r1xwA34KDB

https://github.com/nuric/softuni

DeepLogic: Towards End-to-End Differentiable Logical Reasoning

https://arxiv.org/pdf/1805.07433.pdf

https://github.com/nuric/deeplogic

DeepProbLog: Integrating Logic and Learning through Algebraic Model Counting

https://kr2ml.github.io/2019/papers/KR2ML_2019_paper_34.pdf

Learning Compositional Neural Programs with Recursive Tree Search and Planning

http://papers.nips.cc/paper/9608-learning-compositional-neural-programs-with-recursive-tree-search-and-planning.pdf

https://github.com/instadeepai/AlphaNPI

https://www.instadeep.com/research-article/towards-compositionality-in-deep-reinforcement-learning/

ELABORATION TOLERANCE John McCarthy

http://jmc.stanford.edu/articles/elaboration/elaboration.pdf

Using NLU in Context for Question Answering: Improving on Facebook's bAbI Tasks

https://arxiv.org/abs/1709.04558

Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization

https://arxiv.org/pdf/1906.00180.pdf

Library Learning for Neurally-Guided Bayesian Program Induction

https://papers.nips.cc/paper/8006-learning-libraries-of-subroutines-for-neurallyguided-bayesian-program-induction.pdf

Inductive Learning of Answer Set Programs from Noisy Examples

https://arxiv.org/pdf/1808.08441.pdf

Online Learning of Event Definitions

https://arxiv.org/pdf/1608.00100.pdf

Neural Logic Networks

https://arxiv.org/abs/1910.08629

Relational Neural Machines

https://arxiv.org/pdf/2002.02193.pdf

TensorLog: Deep Learning Meets Probabilistic Databases

https://arxiv.org/pdf/1707.05390.pdf

Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge

https://arxiv.org/pdf/1606.04422.pdf

Differentiable Learning of Logical Rules for Knowledge Base Reasoning

https://arxiv.org/pdf/1702.08367.pdf

Neural-LP: https://github.com/fanyangxyz/Neural-LP

Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP

https://link.springer.com/article/10.1007/s10994-018-5707-3

Surveys

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning

https://arxiv.org/pdf/1905.06088.pdf

Program Synthesis

https://www.microsoft.com/en-us/research/wp-content/uploads/2017/10/program_synthesis_now.pdf

Courses:

Stanford Logic Programming

https://web.stanford.edu/~vinayc/logicprogramming/html/

http://logicprogramming.stanford.edu/chapters/index.html

AI Modern Approach

https://github.com/aimacode/aima-python

МГУ Математическая логика и логическое программирование

ссылка

Software:

Problog

https://dtai.cs.kuleuven.be/problog/index.html

https://problog.readthedocs.io/en/latest/python.html

First Order Inductive Learner (FOIL) algorithm implemented in Python

https://github.com/johntrimble/foil-python