Filters








53 Hits in 5.0 sec

Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension

Francisco S. Marcondes, Dalila Durães, Flávio Santos, José João Almeida, Paulo Novais
2021 Electronics  
This paper explores the use of paraconsistent analysis for assessing neural networks from an explainable AI perspective.  ...  The first was a baseline experiment based on MNIST for establishing the link between paraconsistency and neural networks.  ...  Therefore, this article's objective is to report the findings of an initial attempt at using paraconsistent analysis as an explainable approach.  ... 
doi:10.3390/electronics10212660 fatcat:o23uc24ndfhmpm4i7b67o5ggem

Advances in Sustainable Smart Cities and Territories

Juan M. Corchado, Saber Trabelsi
2022 Electronics  
The smart city concept refers to the implementation of disruptive technologies in the urban environment, with the aim of creating an optimal citizen experience [...]  ...  Paraconsistent analysis has been performed to evaluate the use of neural networks from the standpoint of Explainable AI [3] .  ...  The objective of the initial experiment was to institute the connection between paraconsistency and neural networks, and it was based on MNIST.  ... 
doi:10.3390/electronics11081280 fatcat:d4ac2le54jbxjohbz6ri62ltba

An Expert System Structured in Paraconsistent Annotated Logic for Analysis and Monitoring of the Level of Sea Water Pollutants [chapter]

Joao Inacio Da Silva Filho, Mauricio C., Camilo D. Seabra Pereira, Ana Carolina, Luis Fernando P. Ferrara, Odair Pitoli, Dorotea Vilanova
2011 Expert Systems for Human, Materials and Automation  
It was built a configuration of Paraconsistent Artificial Neural Network (PANN) composed of algorithms based on the principals of Paraconsistent Logic to compose the Expert System with the goal of simulating  ...  With the due information, we will obtain the favorable evidence degree, one of the inputs of the Paraconsistent Neural network.  ...  An Expert System Structured in Paraconsistent Annotated Logic for Analysis and Monitoring of the Level of Sea Water Pollutants, Expert Systems for Human, Materials and Automation, Prof.  ... 
doi:10.5772/17603 fatcat:gqtloujx2vcddfak3gzrg52mrq

Paraconsistent annotated logic applied to industry assets condition monitoring and failure prevention based on vibration signatures

Márcio Pereira Corrêa, Ayslan Cuzzuol Machado, João Inácio da Silva Filho, Dorotéa Vilanova Garcia, Mauricio Conceição Mario, Carlos Teofilo Salinas Sedano
2022 Research, Society and Development  
In this study, we introduced an expert system (ESvbrPAL2v), responsible for monitoring assets based on vibration signature analysis through a set of algorithms based on the Paraconsistent Annotated Logic  ...  The tests to confirm the efficiency of ESvbrPAL2v were performed in analyses initially carried out on small prototypes and, after the initial adjustments, tests were carried out on bearings of a group  ...  Paraconsistent Artificial Neural Cell of Learning -(LPANCell) Paraconsistent Artificial Neural Cell of Learning (LPANCell) is basically an ordinary PANCell having its initials input values (𝛍𝟏𝐀 𝐚𝐧𝐝  ... 
doi:10.33448/rsd-v11i1.25104 fatcat:rvzuyo2mufbzheabjdzgtlbp4e

The General Theory of General Intelligence: A Pragmatic Patternist Perspective [article]

Ben Goertzel
2021 arXiv   pre-print
logical reasoning, program learning, clustering and attention allocation in the context and language of this high level architecture is considered, as is the importance of a common (e.g. typed metagraph based  ...  However, the standard approach to building probability distributions based on Boolean lattices is not the only relevant strategy from an AI point of view.  ...  Metagraphs could be used as a conceptual model of AI systems built using conventional neural net architectures, biologically realistic neural net simulations, topological quantum computing based AI fabrics  ... 
arXiv:2103.15100v3 fatcat:mqomtbl53rfgbbdzqqvlexq4i4

An Approach to Human-Level Commonsense Reasoning [chapter]

Michael L. Anderson, Walid Gomaa, John Grant, Don Perlis
2012 Paraconsistency: Logic and Applications  
paraconsistent logic that may be of some use in implementing commonsense reasoning.  ...  This paper discusses some of the features of human reasoning that may account for this difficulty, surveys a number of reasoning systems and formalisms, and offers an outline of active logic, a non-classical  ...  Figure 11 .1 shows an example of a SNePS semantic network.  ... 
doi:10.1007/978-94-007-4438-7_12 dblp:series/leus/AndersonGGP13 fatcat:ciggfpulmbdxbfvm5rzuan4eyi

Transhumanities as the Pinnacle and a Bridge

Piotr (Peter) Boltuc
2022 Humanities  
This approach turns out to be practical at the epoch of advanced AI.  ...  Artificial Intelligence (AI leading to AGI).  ...  comments on an earlier version; my Senior Seminar students at UIS for their input, as well as anonymous reviewers for this journal for their important recommendations.  ... 
doi:10.3390/h11010027 fatcat:d5qjgivblvei3d3vggygedd6ga

Computing Nature – A Network of Networks of Concurrent Information Processes [chapter]

Gordana Dodig-Crnkovic, Raffaela Giovagnoli
2013 Computing Nature  
through his ideas about morphological computing, "unorganized" (neural-network type) machines and "oracle" machines.  ...  Computational processes running in networks of networks (such as the internet) can be modeled as distributed, reactive, agent-based and concurrent computation.  ...  vehicles -designed by an imitation based i.e. cultural approach.  ... 
doi:10.1007/978-3-642-37225-4_1 fatcat:yf7476oh25hobolz2jsmp6dn54

BICA AND BEYOND: HOW BIOLOGY AND ANOMALIES TOGETHER CONTRIBUTE TO FLEXIBLE COGNITION

DONALD PERLIS
2010 International Journal of Machine Consciousness  
Ongoing investigations based on this approach are discussed, including hypotheses regarding its promise for robust versatile machines.  ...  Evolutionary and cognitive examples are used to motivate an approach to the brittleness problem and automated°exible cognition, centering on the notion of an anomaly as the key focus of processing.  ...  Acknowledgments This material is based upon work supported in part by NSF Grant #IIS0803739, AFOSR Grant #FA95500910144 and ONR Grant #N000140910328.  ... 
doi:10.1142/s1793843010000485 fatcat:lqs62tttk5gg5ja77m4rqdwi6y

AAAI 2008 Workshop Reports

Sarabjot Singh Anand, Razvan C. Bunescu, Vitor R. Carvalho, Jan Chomicki, Vincent Conitzer, Michael T. Cox, Virginia Dignum, Zachary Dodds, Mark Dredze, David Furcy, Evgeniy Gabrilovich, Mehmet H. Göker (+25 others)
2009 The AI Magazine  
from AI Research and Applications; and Wikipedia and Artificial Intelligence: An Evolving Synergy.  ...  ; Human Implications of Human-Robot Interaction; Intelligent Techniques for Web Personalization and Recommender Systems; Metareasoning: Thinking about Thinking; Multidisciplinary Workshop on Advances in  ...  Papers covered a wide range of topics, including regression, classification, reinforcement learning, planning, Markov logic networks, and neural networks.  ... 
doi:10.1609/aimag.v30i1.2196 fatcat:xsrhlc3tgzhzphg3wt57klqvqu

A Survey on the Evolution of the Notion of Context-Awareness

J. Augusto, A. Aztiria, D. Kramer, U. Alegre
2017 Applied Artificial Intelligence  
Based on this context and using a feed-forward neural network, they developed two applications.  ...  Artificial Neural Networks Mozer et al. Mozer et al. (1995) and Chen et al.  ... 
doi:10.1080/08839514.2018.1428490 fatcat:suvchtim55dyxofquxf655fuwy

Resolving conflicts in knowledge for ambient intelligence

Martin Homola, Theodore Patkos, Giorgos Flouris, Ján Šefránek, Alexander Šimko, Jozef Frtús, Dimitra Zografistou, Martin Baláž
2015 Knowledge engineering review (Print)  
As such, it is an interesting and challenging application area for many computer science fields and approaches.  ...  We take a look at a number of KR approaches that may be applied: context modelling, multi-context systems, belief revision, ontology evolution and debugging, argumentation, preferences, and paraconsistent  ...  Acknowledgements This work resulted from the Slovak-Greek bilateral project "Multi-context Reasoning in Heterogeneous environments", registered on the Slovak side under no.  ... 
doi:10.1017/s0269888915000132 fatcat:dsa3goyft5bfxezoaz7iwuuauu

Real Islamic Logic [article]

Jan Aldert Bergstra
2011 arXiv   pre-print
That approach to Islamic Logic should serve modern Islamic objectives in a way comparable to the functionality of Islamic Finance.  ...  Four options for assigning a meaning to Islamic Logic are surveyed including a new proposal for an option named "Real Islamic Logic" (RIL).  ...  LP's. 33 Neural network modeling may prove a more effective technique for predicting ICLPP outcomes.  ... 
arXiv:1103.4515v1 fatcat:rly4acmnn5bxng7tatmu42sjx4

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

Mohamed A. Kassem, Khalid M. Hosny, Robertas Damaševičius, Mohamed Meselhy Eltoukhy
2021 Diagnostics  
The studies are compared based on their contributions, the methods used and the achieved results.  ...  Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems.  ...  Finally, an ensemble classifier network that combined fuzzy neural networks with backpropagation (BP) neural network was used to classify the lesions based on the extracted features.  ... 
doi:10.3390/diagnostics11081390 fatcat:r4gyqfwberfofhcbx2xsn7vpf4

A review on voice pathology: Taxonomy, diagnosis, medical procedures and detection techniques, open challenges, limitations, and recommendations for future directions

Nuha Qais Abdulmajeed, Belal Al-Khateeb, Mazin Abed Mohammed
2022 Journal of Intelligent Systems  
Speech is a primary means of human communication and one of the most basic features of human conduct. Voice is an important part of its subsystems.  ...  Moreover, this study presents different applications, open challenges, and recommendations for future directions of IoT systems and artificial intelligence (AI) approaches in the voice pathology diagnosis  ...  Neural networks and the hidden Markov model (HMM) are among the most popular nonlinear classifiers.  ... 
doi:10.1515/jisys-2022-0058 fatcat:dvh3krao6nfjzengdphvrqqdia
« Previous Showing results 1 — 15 out of 53 results