Filters








41,435 Hits in 1.7 sec

Instinctive Recognition of Pathogens in Rice Using Reformed Fractional Differential Segmentation and Innovative Fuzzy Logic-Based Probabilistic Neural Network

Anusha Preetham, Sayed Sayeed Ahmad, Ihab Wattar, Pooja Singh, Sandeep Rout, Mejdal A. Alqahtani, Enoch Tetteh Amoatey
2022 Journal of Food Quality  
All three previous techniques were surpassed by the proposed fuzzy logic-based probabilistic neural network on a range of performance metrics, with the new network obtaining greater accuracy.  ...  It is important to categorise the photographs based on the recovered feature values, and the suggested novel fuzzy logic-based probabilistic neural network approach may be used to accomplish this task.  ...  Leaf Segmentation Using Partial Differential Technique.  ... 
doi:10.1155/2022/8662254 doaj:a04b30c5c4d14ed2bb938ae472ae894e fatcat:mf6ry7bcffcmlnnymf6vhwmt6e

DeepProbLog: Neural Probabilistic Logic Programming [article]

Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, Thomas Demeester, Luc De Raedt
2018 arXiv   pre-print
To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that  ...  We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates.  ...  They use fuzzy logic to create a differentiable way of measuring how much the output of the neural networks violates these constraints.  ... 
arXiv:1805.10872v2 fatcat:vfybzoabxfd4vazuyizhfxnqfy

From Statistical Relational to Neuro-Symbolic Artificial Intelligence [article]

Luc De Raedt, Sebastijan Dumančić, Robin Manhaeve, Giuseppe Marra
2020 arXiv   pre-print
Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning.  ...  The second category includes Markov Logic Networks (MLNs) [Richardson and Domingos, 2006] and Probabilistic Soft Logic (PSL) [Bach et al., 2017] .  ...  But rather than focusing on how to integrate logic and neural networks, it is centred around the question of how to integrate logic with probabilistic graphical models.  ... 
arXiv:2003.08316v2 fatcat:tlgua7bvyvbftcnlngn7drix34

Predicting Strategic Behavior from Free Text (Extended Abstract)

Omer Ben-Porat, Lital Kuchy, Sharon Hirsch, Guy Elad, Roi Reichart, Moshe Tennenholtz
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
But rather than focusing on integrating logic and neural networks, it is centred around the question of integrating logic with probabilistic reasoning, more specifically probabilistic graphical models.  ...  The second category includes Markov Logic Networks (MLNs) [Richardson and Domingos, 2006] and Probabilistic Soft Logic (PSL) [Bach et al., 2017] .  ... 
doi:10.24963/ijcai.2020/688 dblp:conf/ijcai/RaedtDMM20 fatcat:kbp4p2slsrculnqg2ig2dvchde

From Statistical Relational to Neural Symbolic Artificial Intelligence: a Survey [article]

Giuseppe Marra and Sebastijan Dumančić and Robin Manhaeve and Luc De Raedt
2022 arXiv   pre-print
Neural-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning.  ...  Example 9 (Markov Logic Networks). We show a probabilistic extension (adapted from [92] ) of the theory in Example 4 using the formalism of Markov Logic Networks.  ...  This is used in well known systems such as Markov Logic Networks (MLNs) [92] , Probabilistic Soft Logic (PSL) [3] , Bayesian Logic Programs (BLPs) [56] and Probabilistic Relational Models (PRMs) [  ... 
arXiv:2108.11451v2 fatcat:2vynob3s7bhsjk22pwv5e5hnta

Neural Probabilistic Logic Programming in DeepProbLog [article]

Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, Thomas Demeester, Luc De Raedt
2019 arXiv   pre-print
To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that  ...  We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates.  ...  They use fuzzy logic to create a differentiable way of measuring how much the output of the neural networks violates these constraints.  ... 
arXiv:1907.08194v2 fatcat:cxspnmb6uverdgn6k7ssmfi2oe

Neural probabilistic logic programming in DeepProbLog

Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, Thomas Demeester, Luc De Raedt
2021 Artificial Intelligence  
To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that  ...  We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates.  ...  They use fuzzy logic to create a differentiable way of measuring how much the output of the neural networks violates these constraints.  ... 
doi:10.1016/j.artint.2021.103504 fatcat:kjlerx7wxjdzdfpguarh5uhdwa

Converting networks to predictive logic models from perturbation signalling data with CellNOpt [article]

Enio Gjerga, Panuwat Trairatphisan, Attila Gabor, Hermann Koch, Celine Chevalier, Francesco Ceccarelli, Aurelien Dugourd, Alexander Mitsos, Julio Saez-Rodriguez
2020 bioRxiv   pre-print
These updates include (i) an Integer Linear Programming (ILP) formulation which guarantees efficient optimisation for Boolean models, (ii) a probabilistic logic implementation for semi-quantitative datasets  ...  Results: CellNOpt is a collection of Bioconductor R packages for building logic models from perturbation data and prior knowledge of signalling networks.  ...  CellNOpt features different formalisms ranging from Boolean logic to logic-based ordinary differential equations (logic-ODE).  ... 
doi:10.1101/2020.03.04.976852 fatcat:4her7huuzjfq3bdcvoutejz4ey

Emergence of robust regulatory motifs from in silico evolution of sustained oscillation

Yaochu Jin, Yan Meng
2011 Biosystems (Amsterdam. Print)  
Our simulation results indicate that both evolvability and robustness of the considered regulatory motifs depend on the cis-regulation logic and the way in which positive and negative feedback loops are  ...  This paper investigates in silico the influence of the cis-regulation logic and the coupling of feedback loops on the evolvability and robustness of gene regulatory motifs that can generate sustained oscillation  ...  The two binary bits for encoding the regulation logic can be decoded into an integer number between 0 and 3, which represents the Zadeh 'AND' logic (0), the probabilistic 'AND' (1), the probabilistic '  ... 
doi:10.1016/j.biosystems.2010.09.009 pmid:20920549 fatcat:k2j3af3us5gh5daijp5wkfx2mu

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.  ...  To the best of our knowledge, Meta_Abd is the first system that can jointly learn neural networks from scratch and induce recursive first-order logic theories with predicate invention.  ...  The second author acknowledges support from the UK's EPSRC Human-Like Computing Network, grant EP/R022291/1, for which he acts as director.  ... 
arXiv:2010.03514v2 fatcat:6mtsp6ucvnafnme47sama6vuru

Modelling techniques for biomolecular networks [article]

Gerhard Mayer
2020 arXiv   pre-print
Then we show the advantages of Boolean networks models over more mechanistic modelling types like differential equation techniques.  ...  We also give a short overview about the mathematical frameworks for modelling of logical networks and list available software packages for logical modelling.  ...  The advantage is that AND-NOT networks can be handled with up to 1 million nodes. [69, 70] Probabilistic Boolean Networks (PBN) Probabilistic Boolean network introduce a stochastic element.  ... 
arXiv:2003.00327v1 fatcat:ldcslhpgdrhfpavwypbx2c6qxu

Influence of regulation logic on the easiness of evolving sustained oscillation for gene regulatory networks

Yaochu Jin, Yan Meng, Bernhard Sendhoff
2009 2009 IEEE Symposium on Artificial Life  
Two forms of fuzzy logic, namely, the Zadeh operators and the probabilistic operators, as well as the summation logic have been investigated.  ...  This paper investigates empirically the influence of regulation logic on the dynamics of two computational models of genetic regulatory network motifs.  ...  sum and probabilistic 'OR' as the regulation logic, respectively.  ... 
doi:10.1109/alife.2009.4937695 dblp:conf/ieeealife/JinMS09 fatcat:ggpkyh6g5jaktabwyamljz5fwe

DeepStochLog: Neural Stochastic Logic Programming [article]

Thomas Winters, Giuseppe Marra, Robin Manhaeve, Luc De Raedt
2021 arXiv   pre-print
We show that inference and learning in neural stochastic logic programming scale much better than for neural probabilistic logic programs.  ...  Recent advances in neural symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates.  ...  Third, many systems in the neural symbolic community [11, 10, 37] obtain differentiable logics by relaxing logical programs or theories using fuzzy logic and t-norms.  ... 
arXiv:2106.12574v1 fatcat:4gllqnj2nzekdedkppg7hlsmo4

TensorLog: A Differentiable Deductive Database [article]

William W. Cohen
2016 arXiv   pre-print
To address this problem, we describe a probabilistic deductive database, called TensorLog, in which reasoning uses a differentiable process.  ...  We also present experimental results with TensorLog and discuss its relationship to other first-order probabilistic logics.  ...  Many first-order probabilistic models are implemented by "grounding", i.e., conversion to a more traditional representation. 1 For example, Markov logic networks (MLNs) are a widely-used probabilistic  ... 
arXiv:1605.06523v2 fatcat:3f5aloqqinaaxbyzxqr7vrsgoy

Scientific Theories and Artificial Intelligence [article]

Philippe Desjardins-Proulx, Timothée Poisot, Dominique Gravel
2017 bioRxiv   pre-print
On the other hand, probabilistic machine learning techniques such as deep learning offer an opportunity to tackle large complex problems that are out of the reach of traditional theory-making.  ...  Yet recent studies have shown that deep learning can be useful to logic systems and vice versa.  ...  Fuzzy logic then defines how operators such 198 as and and ⇒ behave with fuzzy values. 199 Both Markov logic networks and probabilistic soft logic define a probability distribution 200 over logic formulas  ... 
doi:10.1101/161125 fatcat:olr3xdvbofai3ngpslb5rx26mi
« Previous Showing results 1 — 15 out of 41,435 results