350 Hits in 4.9 sec

Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps

Martin Stetter, Elmar W. Lang, Jianli Liu
2021 Computational Intelligence and Neuroscience  
Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures.  ...  For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment.  ...  Acknowledgments e authors wish to thank Monika Stetter for numerous valuable discussions on the subject. MS was on sabbatical leave joining the CIML Lab at the University of Regensburg.  ... 
doi:10.1155/2021/5590445 pmid:34804145 pmcid:PMC8604601 fatcat:o5odao4rnzaaxpvjhhikopwbnu

Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps [article]

Martin Stetter, Elmar W. Lang
2021 arXiv   pre-print
Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures.  ...  For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment.  ...  Acknowledgments The authors wish to thank Monika Stetter for numerous valuable discussions on the subject. MS was on sabbatical leave joining the CIML Lab at University of Regensburg.  ... 
arXiv:2007.01647v3 fatcat:wrv62evc25b4rbzlgu7b6j2zjm

On the Learnability of Physical Concepts: Can a Neural Network Understand What's Real? [article]

Alessandro Achille, Stefano Soatto
2022 arXiv   pre-print
DeepFakes and spoofing highlight the feebleness of the link between physical reality and its abstract representation, whether learned by a digital computer or a biological agent.  ...  On the other hand, architectures that incorporate recursion can represent a significantly larger class of concepts, but may still be unable to learn them from a finite dataset.  ...  However, for a shared dictionary to emerge, agents must be immersed in a shared medium, and form independent representations of physical concepts that are simultaneously experienced through independent  ... 
arXiv:2207.12186v2 fatcat:nratucibkneunlloqe3vqwok4m

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence [article]

Nicholas Roy, Ingmar Posner, Tim Barfoot, Philippe Beaudoin, Yoshua Bengio, Jeannette Bohg, Oliver Brock, Isabelle Depatie, Dieter Fox, Dan Koditschek, Tomas Lozano-Perez, Vikash Mansinghka (+8 others)
2021 arXiv   pre-print
Contrary to viewing embodied intelligence as another application domain for machine learning, here we argue that it is in fact a key driver for the advancement of machine learning technology.  ...  In particular, the purview of embodied intelligent agents extends significantly beyond the typical considerations of main-stream machine learning approaches, which typically (i) do not consider operation  ...  Leslie Kaelbling assisted with several ideas in this paper, and her considerable time and help is also very gratefully acknowledged.  ... 
arXiv:2110.15245v1 fatcat:juxc4tai2jbklpul55loccnp7e

Communication-Efficient Edge AI: Algorithms and Systems [article]

Yuanming Shi, Kai Yang, Tao Jiang, Jun Zhang, Khaled B. Letaief
2020 arXiv   pre-print
In this paper, we present a comprehensive survey of the recent developments in various techniques for overcoming these communication challenges.  ...  Artificial intelligence (AI) has achieved remarkable breakthroughs in a wide range of fields, ranging from speech processing, image classification to drug discovery.  ...  Zhi Ding from the University of California at Davis for insightful and constructive comments to improve the presentation of this work.  ... 
arXiv:2002.09668v1 fatcat:nhasdzb7t5dt5brs2r7ocdzrnm

Machine learning & artificial intelligence in the quantum domain: a review of recent progress

Vedran Dunjko, Hans J Briegel
2018 Reports on progress in physics (Print)  
For instance, quantum computing is finding a vital application in providing speed-ups for machine learning problems, critical in our "big data" world.  ...  This deals with questions of the very meaning of learning and intelligence in a world that is fully described by quantum mechanics.  ...  In contrast to such strictly behavioral and operational points of view, an alternative approach towards whole agents (or complete intelligent agents) focuses on agent architectures and cognitive architectures  ... 
doi:10.1088/1361-6633/aab406 pmid:29504942 fatcat:mub6kfcmnrgnpebtbf35lycyly

Edge Caching in Fog-Based Sensor Networks through Deep Learning-Associated Quantum Computing Framework

Tayyabah Hasan, Fahad Ahmad, Muhammad Rizwan, Nasser Alshammari, Saad Awadh Alanazi, Iftikhar Hussain, Shahid Naseem, Daqing Gong
2022 Computational Intelligence and Neuroscience  
Mobile edge computing (MEC) is a new era of digital communication and has a rising demand for intelligent devices and applications.  ...  The framework is basically a merger of a deep learning (DL) agent deployed at the network edge with a quantum memory module (QMM).  ...  of R, d, and w E at a specific time, quantum t is shared in Step 1.  ... 
doi:10.1155/2022/6138434 pmid:35035461 pmcid:PMC8759837 fatcat:gzjswvt6djcmjihksu5x3hs3de

Intelligent D-Band wireless systems and networks initial designs

Marco Di Renzo, Xuewen Qian, Halid Hrasnica, Nikos Katzouris, Kyriakos Manganaris, Dimitris Selimis, Fotis Lazarakis, Tachporn Sanguanpuak, Heikki Halmetoja, Moamen Ibrahim, Edwin Yaqub, Rachana Desai (+5 others)
2021 Zenodo  
The different chapters present system level, simulation and algorithmic models based on multi-agent reinforcement learning, deep reinforcement learning, learning automata for complex event forecasting,  ...  This deliverable gives the results of the ARIADNE project's Task 4.2: Machine Learning based network intelligence.  ...  Multi-Agent Reinforcement Learning Multi-agent reinforcement learning is a subfield of reinforcement learning that focuses on systems with multiple independent learning agents acting in a shared environment  ... 
doi:10.5281/zenodo.5718378 fatcat:l3rkacgotzazha564nqm6wchiy

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey [article]

Xiaofei Wang and Yiwen Han and Victor C.M. Leung and Dusit Niyato and Xueqiang Yan and Xu Chen
2019 arXiv   pre-print
In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management  ...  However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of "providing artificial intelligence for every person and every organization at everywhere  ...  For the downlink, the weights of the global DL model are reshaped into a vector, and then subsampling and quantization are applied [203] .  ... 
arXiv:1907.08349v2 fatcat:4hfqgdto4fhvlguwfjxuz3ik5q

Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration [article]

Henna Kokkonen, Lauri Lovén, Naser Hossein Motlagh, Juha Partala, Alfonso González-Gil, Ester Sola, Iñigo Angulo, Madhusanka Liyanage, Teemu Leppänen, Tri Nguyen, Víctor Casamayor Pujol, Panos Kostakos (+5 others)
2022 arXiv   pre-print
To justify the claim, we provide a general definition for continuum orchestration, and look at how current and emerging orchestration paradigms are suitable for the computing continuum.  ...  In this article, we study orchestration in the device-edge-cloud continuum, and focus on AI for edge, that is, the AI methods used in resource orchestration.  ...  ACKNOWLEDGMENT The authors would like to thank the researchers and alumni at the Center for Ubiquitous Computing (UBICOMP) at the University of Oulu, and Distributed Systems Group (DSG) at TU Wien, for  ... 
arXiv:2205.01423v2 fatcat:phywaj2btrhpnobpeo5z4d3jv4

Advanced Applications of Neural Networks and Artificial Intelligence: A Review

Koushal Kumar, Gour Sundar Mitra Thakur
2012 International Journal of Information Technology and Computer Science  
Artificial Neural Network is a branch of Artificial intelligence and has been accepted as a new computing technology in computer science fields.  ...  Artificial Neural Networks have abundant features including high processing speeds and the ability to learn the solution to a problem from a set of examples.  ...  The model is learnt in an unsupervised manner by tracking objects over long image sequences, and is based on a combination of a neural network implementing Vector Quantization and a type of neuron with  ... 
doi:10.5815/ijitcs.2012.06.08 fatcat:pjdstjcnuzhwlg4rex2uwfrexe

ToyArchitecture: Unsupervised Learning of Interpretable Models of the World [article]

Jaroslav Vítků, Petr Dluhoš, Joseph Davidson, Matěj Nikl, Simon Andersson, Přemysl Paška, Jan Šinkora, Petr Hlubuček, Martin Stránský, Martin Hyben, Martin Poliak, Jan Feyereisl (+1 others)
2019 arXiv   pre-print
In this paper, we present a novel, purposely simple, and interpretable hierarchical architecture which combines multiple different mechanisms into one system: unsupervised learning of a model of the world  ...  In contrast with purely theoretical approaches, the resulting architecture should be usable in realistic settings, but also form the core of a framework containing all the basic mechanisms, into which  ...  This paper is structured as follows: first, we state the basic premises for a situated intelligent agent and review the important areas in which current Deep Learning (DL) methods do not perform well (  ... 
arXiv:1903.08772v2 fatcat:wnknrw73pfhnpi6zy35pecriom

Resource-aware event triggered distributed estimation over adaptive networks

Ihsan Utlu, O. Fatih Kilic, Suleyman S. Kozat
2017 Digital signal processing (Print)  
We propose a novel algorithm for distributed processing applications constrained by the available communication resources using diffusion strategies that achieves up to a 10 3 fold reduction in the communication  ...  parameter, resulting in a greatly reduced communication requirement.  ...  Acknowledgments This work is in part supported by the TUBITAK project Contract No.: 115E917.  ... 
doi:10.1016/j.dsp.2017.05.011 fatcat:uq4jletclzdhdicaovzfxv6swe

Roadmap for Edge AI: A Dagstuhl Perspective [article]

Aaron Yi Ding, Ella Peltonen, Tobias Meuser, Atakan Aral, Christian Becker, Schahram Dustdar, Thomas Hiessl, Dieter Kranzlmuller, Madhusanka Liyanage, Setareh Magshudi, Nitinder Mohan, Joerg Ott (+7 others)
2021 arXiv   pre-print
In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimization, and deployment of distributed AI/ML pipelines  ...  Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI.  ...  ACKNOWLEDGMENTS The discussions leading to this editorial were initiated in Dagstuhl Seminar 21342 on Identifying Key Enablers in Edge Intelligence, and we thank all participants for their contributions  ... 
arXiv:2112.00616v1 fatcat:o7dnuchbq5gf7hmfos2kberevm

6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications [article]

Emilio Calvanese Strinati, Sergio Barbarossa
2021 arXiv   pre-print
The goal of this paper is to promote the idea that including semantic and goal-oriented aspects in future 6G networks can produce a significant leap forward in terms of system effectiveness and sustainability  ...  Combining knowledge representation and reasoning tools with machine learning algorithms paves the way to build semantic learning strategies enabling current machine learning algorithms to achieve better  ...  The proposed new three-levels architecture for 6G is represented schematically in Fig. 3 . Fig. 3 has five columns.  ... 
arXiv:2011.14844v3 fatcat:7pz7tlylh5gu3gy7wry2ankmw4
« Previous Showing results 1 — 15 out of 350 results