41,110 Hits in 4.6 sec

Neural ensemble decoding for topological quantum error-correcting codes [article]

Milap Sheth, Sara Zafar Jafarzadeh, Vlad Gheorghiu
2019 arXiv   pre-print
In this paper, we introduce a framework which can combine arbitrary decoders for any given code to significantly reduce the logical error rates.  ...  We use machine learning techniques to assign a given error syndrome to the decoder which is likely to decode it correctly.  ...  S.Z. acknowledges support from "NSERC CREATE in Building a Workforce for the Cryptographic Infrastructure of the 21st Century (CryptoWorks21)" and "Quantum Information Science, Cryptography and Privacy  ... 
arXiv:1905.02345v1 fatcat:zrsfz4k4wbhydodcfc4aslt3iy

A Topology Graph Algorithm Based on Lattice-Valued Logic to Solve Satisfiability Problems

Jieqing Tan, Yingjie Li, Giuseppe D'Aniello
2022 Mathematical Problems in Engineering  
For further improving the efficiency, a topology graph deduction is proposed as well as its soundness, completeness, and universal algorithm.  ...  Automatic reasoning is a very challenging research area in the field of artificial intelligence.  ...  In this paper, a topology graph algorithm based on the principle of lattice-valued logic is presented.  ... 
doi:10.1155/2022/2677457 fatcat:dxqcre3fy5h4bfobacrzihvn4i

Quantum-assisted associative adversarial network: applying quantum annealing in deep learning

Max Wilson, Thomas Vandal, Tad Hogg, Eleanor G. Rieffel
2021 Quantum Machine Intelligence  
This novel hybrid quantum-classical algorithm joins a growing family of algorithms that use a quantum processor sampling subroutine in deep learning, and provides a scalable framework to test the advantages  ...  In this work, we present an algorithm for learning a latent variable generative model via generative adversarial learning where the canonical uniform noise input is replaced by samples from a graphical  ...  The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material.  ... 
doi:10.1007/s42484-021-00047-9 fatcat:fosotnbbb5eela72ouos5o4hem

Toward a role model

Roded Sharan
2013 EMBO Reports  
In particular, such a pipeline requires piecing together the learning of topology, annotation and logic to optimize a common objective.  ...  This framework quantitatively describes the network's fluxes under a steady-state assumption, which allows the in silico simulation of any process of interest under different genetic and environmental  ... 
doi:10.1038/embor.2013.161 pmid:24126764 pmcid:PMC3818069 fatcat:wmubjgzfabe2hd4xkgohrm6n3e

Facets of Artificial General Intelligence

Kai-Uwe Kühnberger, Pascal Hitzler
2009 Künstliche Intelligenz  
This positive assessment of the very possibility of AGI has partially its roots in the development of new methodological achievements in the AI area, like new learning paradigms and new integration techniques  ...  We argue that time has come for a serious endeavor to work towards artificial general intelligence (AGI).  ...  Neural techniques have been pushed further by new topologies and learning algorithms of the network: not only learning by backpropagation of errors in feedforward networks, but also network topologies  ... 
dblp:journals/ki/KuhnbergerH09 fatcat:zjd5sq6mx5hdtiquj5lmgni3pq

The Wyred Project: A Technological Platform For A Generative Research And Dialogue About Youth Perspectives And Interests In Digital Society

Francisco José García-Peñalvo
2016 Zenodo  
The WYRED Project: A Technological Platform for a Generative Research and Dialogue about Youth Perspectives and Interests in Digital Society. Journal of Information Technology Research, 9(4), vi-x.  ...  In that layer, the glyphs of a single grapheme share some topological attributes in common.  ...  These common topological attributes form a main identity of a grapheme, which is called Common Identity template that is obtained by means of Supervised Learning method.  ... 
doi:10.5281/zenodo.208352 fatcat:3h6gh3kwurfytntpp57sfhm334

Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning [article]

Max Wilson, Thomas Vandal, Tad Hogg, Eleanor Rieffel
2019 arXiv   pre-print
This algorithm joins a growing family of algorithms that use a quantum annealing subroutine in deep learning, and provides a framework to test the advantages of quantum-assisted learning in GANs.  ...  The quantum-assisted associative adversarial network successfully learns a generative model of the MNIST dataset for all topologies, and is also applied to the LSUN dataset bedrooms class for the Chimera  ...  We would also like to thank Thomas Vandal, Rama Nemani, Andrew Michaelis, Subodh Kalia and Salvatore Mandra for useful discussions and comments.  ... 
arXiv:1904.10573v1 fatcat:pue7olofxbg6zgh2gafkqjdogi

Argumentative Topology: Finding Loop(holes) in Logic [article]

Sarah Tymochko, Zachary New, Lucius Bynum, Emilie Purvine, Timothy Doster, Julien Chaput, Tegan Emerson
2020 arXiv   pre-print
To this end we present a novel framework that we call Topological Word Embeddings which leverages mathematical techniques in dynamical system analysis and data driven shape extraction (i.e. topological  ...  In this preliminary work we show that using a topological delay embedding we are able to capture and extract a different, shape-based notion of logic aimed at answering the question "Can we find a circle  ...  and "What can we learn from the shape of logical constructs?" We have shown that one can in fact detect the presence of topological circles in circular logic.  ... 
arXiv:2011.08952v1 fatcat:2fwgf65h3ze2xpxyerr3daxz7i

Review on Fog Based Spectrum Sensing for Artificial Intelligence

A. Rethina Palin, I. Jeena Jacob
2018 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
A Markov logic network (MLN) based reasoning engine is utilized for the final routing table updating regarding the system uncertainty and complexity.  ...  The cluster head (CH) manages a group of nodes such that the network has the hierarchical structure for the channel access, routing and bandwidth allocation.  ...  Initially as a first step the executable form of the application is to be created and loaded in the common server machine which is accessible to all the user and the server is to be connected to a network  ... 
doi:10.32628/cseit183816 fatcat:4eaejv46rrc3vmhoi5hkrhvaxy

Four-Layer Grapheme Model for Computational Paleography

Raymond E.I. Pardede, Loránd L. Tóth, György A. Jeney, Ferenc Kovács, Gábor Hosszú
2016 Journal of Information Technology Research  
These common topological attributes form a main identity of a grapheme, which is called Common Identity template that is obtained by means of Supervised Learning method.  ...  When trying to describe the logical relation of various glyphs, their topological properties must be examined in a higher layer framework so called Visual Identity Layer.  ...  Also in writing system, glyph in general refers to a unique shape (an image) that represents a single grapheme and contains topological information about the shape of the grapheme.  ... 
doi:10.4018/jitr.2016100105 fatcat:weyfnhu2bjg6njwa7qbbbp3bie

Generalized Mean Estimation in Monte-Carlo Tree Search

Tuan Dam, Pascal Klink, Carlo D'Eramo, Jan Peters, Joni Pajarinen
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
We call our new approach Power-UCT, and argue how the use of the power mean operator helps to speed up the learning in MCTS.  ...  In UCT, a tree with nodes (states) and edges (actions) is incrementally built by the expansion of nodes, and the values of nodes are updated through a backup strategy based on the average value of child  ...  Then, we design the LE algorithm with the topological structure from the common representation and all views. The whole framework of TMV-LE is shown in Figure 1 .  ... 
doi:10.24963/ijcai.2020/328 dblp:conf/ijcai/ZhangJL20 fatcat:2ekj34u36rdnxab6jq356bizsi

An adaptive scheduling framework for heterogeneous computer networks

John S. Hollywood, Kenneth N. McKay
2004 Control Engineering Practice  
The presented framework detects changes in the job stream, and other events, and evolves scheduling policies at two distinct levels-operational and tactical-in response to the changes, making adaptations  ...  The paper also presents a simulation of a computer network facing dynamic job arrival rates, which demonstrates that even a simple implementation of the framework can lead to major gains in performance  ...  The authors would like to express their gratitude to the referees for the insightful and constructive criticism provided.  ... 
doi:10.1016/s0967-0661(03)00172-2 fatcat:qx5coy42cba3li5psdi5d26vga

The Logic Fundamentals of Machine Consciousness: Theory of Tri-state

2022 Journal of Robotics and Automation Research  
The second part of this paper designs a machine-consciousness model framework based on the "Theory of Tri-state" (Tri-state Logic).  ...  For a long time, the system of scientific methodology has been composed of logic, empirical (falsification), qualitative, quantitative and deterministic, and corresponding thinking tools.  ...  In other words, the concept of mathematical calculation behind the current computer depth learning framework is essentially to combine some differentiable computing units into a program, and then adjust  ... 
doi:10.33140/jrar.03.01.07 fatcat:vjii4h2trnebbp3aqtff3m2jzy

Scaling the HTM Spatial Pooler

Damir Dobric, Andreas Pech, Bogdan Ghita, Thomas Wennekers
2020 International Journal of Artificial Intelligence & Applications  
A complex topology and high number of neurons used in this algorithm, require more computing power than even a single machine with multiple cores or a GPUs could provide.  ...  The Hierarchical Temporal Memory Cortical Learning Algorithm (HTM CLA) is a theory and machine learning technology that aims to capture cortical algorithm of the neocortex.  ...  Figure 7 . 7 Spatial Pooler-MT compute time in milliseconds in dependence of column topology. Figure 8 . 8 Learning time in [ms] of a MNIST image 28x28 with 200x200 Columns.  ... 
doi:10.5121/ijaia.2020.11407 fatcat:gvcoojnkubgjvjbjzhqf5q36by

Local structure supports learning of deterministic behavior in recurrent neural networks

Jonathan Binas, Giacomo Indiveri, Michael Pfeiffer
2015 BMC Neuroscience  
In this study, we present a recurrent neural network based on biologically plausible circuit motifs, which is able to learn such deterministic behavior from sensory input and reinforcement signals.  ...  This type of computation can be modeled conveniently in the framework of finite automata.  ...  This mechanism leads to reconfiguration of the network connectivity in such a way that a desired behavior is learned from sequences of inputs and reward signals.  ... 
doi:10.1186/1471-2202-16-s1-p195 pmcid:PMC4698769 fatcat:uoilya254ffqfavjdoxxytrq5y
« Previous Showing results 1 — 15 out of 41,110 results