Filters








1,817 Hits in 7.5 sec

A National Network of Neurotechnology Centers for the BRAIN Initiative

A. Paul Alivisatos, Miyoung Chun, George M. Church, Ralph J. Greenspan, Michael L. Roukes, Rafael Yuste
2015 Neuron  
We propose the creation of a national network of neurotechnology centers to enhance and accelerate the BRAIN Initiative and optimally leverage the effort and creativity of individual laboratories involved  ...  As "brain observatories," these centers could provide the critical interdisciplinary environment both for realizing ambitious and complex technologies and for providing individual investigators with access  ...  Strong connections between the various ''nodes'' of a national network of centers might be facilitated and coordinated by a single ''hub''-perhaps orchestrating a network of several national laboratories  ... 
doi:10.1016/j.neuron.2015.10.015 pmid:26481036 pmcid:PMC5283530 fatcat:cqovnfbvgrc7hpkti37tdgtopa

Brain-inspired computing

Steve B. Furber
2016 IET Computers & Digital Techniques  
SpiNNaker (Spiking Neural Network Architecture) is one such large-scale example, and much has been learnt in the design, development and commissioning of this machine that will inform future developments  ...  Although there are, as yet, few compelling demonstrations of the advantages of such approaches in engineered systems, a number of large-scale platforms have been developed recently that promise to accelerate  ...  exploration of the capabilities of the machine is supported by the European Research Council under the European Union's Seventh Framework Programme (FP7/2007-2013) / ERC grant agreement 320689.  ... 
doi:10.1049/iet-cdt.2015.0171 fatcat:2k4phkqpzfggfmqvd5hzl355dy

Intelligent finance—an emerging direction

Heping Pan, Didier Sornette, Kenneth Kortanek
2006 Quantitative finance (Print)  
Intelligent finance represents a new direction recently emerging from the confluence of several distinct disciplines in financial market analysis, investing and trading, removing any historical or artificial  ...  As a comprehensive approach, it is a quest for absolute positive and nontrivial returns in investing and trading via exploiting the complete information about the financial markets from all general perspectives  ...  As a comprehensive approach to high finance, intelligent finance is a quest for absolute positive and nontrivial returns in investing and trading by means of exploiting the complete information about the  ... 
doi:10.1080/14697680600760753 fatcat:lkmwdg7aszhdrd2af7noiy76le

Neuromorphic Processing and Sensing: Evolutionary Progression of AI to Spiking [article]

Philippe Reiter, Geet Rose Jose, Spyridon Bizmpikis, Ionela-Ancuţa Cîrjilă
2020 arXiv   pre-print
Neuromorphic technologies based on Spiking Neural Network algorithms hold the promise to implement advanced artificial intelligence using a fraction of the computations and power requirements by modeling  ...  First-hand, experimental results of converting a VGG-16 neural network to an SNN are shared.  ...  The depth of knowledge, experience and patience exhibited by those mentioned facilitated this research and enabled the results achieved.  ... 
arXiv:2007.05606v1 fatcat:mw7nczubnzao3l73kyibxyvjpy

Structuring Intelligence: The Role of Hierarchy, Modularity and Learning in Generating Intelligent Behaviour [chapter]

Joanna J. Bryson
2012 The Complex Mind  
Genetic evolution might also be viewed as a process of learning -a means by which species and therefore individuals within species acquire behaviour.  ...  latencies associated with having to revisit every step of a hierarchy (a criticism of hierarchy due to Maes, 1991) .  ... 
doi:10.1057/9780230354456_7 fatcat:ifzdgvfssbgv5ikgnsyhvezuva

Testing and verification of neural-network-based safety-critical control software: A systematic literature review

Jin Zhang, Jingyue Li
2020 Information and Software Technology  
Context: Neural Network (NN) algorithms have been successfully adopted in a number of Safety-Critical Cyber-Physical Systems (SCCPSs).  ...  Method: By searching the six most relevant digital libraries, we retrieved 950 papers on the T&V of NN-based Safety-Critical Control Software (SCCS).  ...  This work is also supported by the Management of safety and security risks for cyber-physical systems project, which is financed by the Norwegian University of Technolgy in collaboration with the Technical  ... 
doi:10.1016/j.infsof.2020.106296 fatcat:3bamhnoqsjcmfkwg33jizjxype

Using satellite imagery to understand and promote sustainable development [article]

Marshall Burke, Anne Driscoll, David B. Lobell, Stefano Ermon
2020 arXiv   pre-print
Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy.  ...  We quantify the paucity of ground data on key human-related outcomes and the growing abundance and resolution (spatial, temporal, and spectral) of satellite imagery.  ...  ., and S.E. are co-founders of AtlasAI, a company that uses machine learning to measure economic outcomes in the developing world.  ... 
arXiv:2010.06988v1 fatcat:c2sx7ftscncofjjyibyyszqztu

Seismic assessment of structures and lifelines

M. Fragiadakis, D. Vamvatsikos, M.G. Karlaftis, N.D. Lagaros, M. Papadrakakis
2015 Journal of Sound and Vibration  
A B S T R A C T We discuss the current state-of-the-art on the assessment of systems (structures and lifelines) subjected to seismic loading.  ...  Emphasis is given to probabilistic performance estimation frameworks and the rational treatment of uncertainty, a major element of contemporary earthquake engineering.  ...  In an effort to improve the robustness of the approximation procedure the polynomial representation of RS is replaced by an approximation produced by neural networks.  ... 
doi:10.1016/j.jsv.2013.12.031 fatcat:pcuwnxkji5hs5b6w6qr33n5goq

Troubling Trends in Machine Learning Scholarship [article]

Zachary C. Lipton, Jacob Steinhardt
2018 arXiv   pre-print
impresses rather than clarifies, e.g., by confusing technical and non-technical concepts; and (iv) misuse of language, e.g., by choosing terms of art with colloquial connotations or by overloading established  ...  of empirical gains, e.g., emphasizing unnecessary modifications to neural architectures when gains actually stem from hyper-parameter tuning; (iii) mathiness: the use of mathematics that obfuscates or  ...  We also thank the ICML Debates organizers for the opportunity to work on this draft and for their patience throughout our revision process.  ... 
arXiv:1807.03341v2 fatcat:7xrlzv2hc5auhl5xe5cg2p5f6m

Deep Learning in Mobile and Wireless Networking: A Survey [article]

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 arXiv   pre-print
In this paper we bridge the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas.  ...  The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure.  ...  We illustrate the principles of the learning and inference processes of a deep neural network in Fig. 3 Fig. 3 : Illustration of the learning and inference processes of a 4-layer CNN. w (·) denote  ... 
arXiv:1803.04311v3 fatcat:awuvyviarvbr5kd5ilqndpfsde

Applications and Techniques for Fast Machine Learning in Science [article]

Allison McCarn Deiana, Joshua Agar, Michaela Blott, Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Scott Hauck, Mia Liu, Mark S. Neubauer, Jennifer Ngadiuba, Seda Ogrenci-Memik, Maurizio Pierini (+74 others)
2021 arXiv   pre-print
The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for  ...  This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.  ...  There is an opportunity to deploy neural networks on GPU or FPGA hardware accelerators to approximate and accelerate this pipeline by orders of magnitude.  ... 
arXiv:2110.13041v1 fatcat:cvbo2hmfgfcuxi7abezypw2qrm

Deep Learning in Mobile and Wireless Networking: A Survey

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 IEEE Communications Surveys and Tutorials  
In this paper we bridge the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas.  ...  The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure.  ...  We illustrate the principles of the learning and inference processes of a deep neural network in Fig. 3 Fig. 3 : Illustration of the learning and inference processes of a 4-layer CNN. w (·) denote  ... 
doi:10.1109/comst.2019.2904897 fatcat:xmmrndjbsfdetpa5ef5e3v4xda

Progress in neuromorphic photonics

Thomas Ferreira de Lima, Bhavin J. Shastri, Alexander N. Tait, Mitchell A. Nahmias, Paul R. Prucnal
2017 Nanophotonics  
By bridging the mathematical prowess of artificial neural networks to the underlying physics of optoelectronic devices, neuromorphic photonics could breach new domains of information processing demanding  ...  The proposed photonic architecture revolves around the processing network node composed of two parts: a nonlinear element and a network interface.  ...  In principle, the neighboring channel could counter this effect by slightly reducing the amount of heat its heater generates.  ... 
doi:10.1515/nanoph-2016-0139 fatcat:rqa7k7bjmzgnbcmokjpfoetbru

A Comprehensive Survey on Particle Swarm Optimization Algorithm and Its Applications

Yudong Zhang, Shuihua Wang, Genlin Ji
2015 Mathematical Problems in Engineering  
Particle swarm optimization (PSO) is a heuristic global optimization method, proposed originally by Kennedy and Eberhart in 1995. It is now one of the most commonly used optimization techniques.  ...  This survey presented a comprehensive investigation of PSO.  ...  [115] constructed three different types of neural network based models, that is, Elman network, generalized regression neural network (GRNN), and wavelet neural network (WNN) constructed by three nonoverlapping  ... 
doi:10.1155/2015/931256 fatcat:ubc5eywnhzdjllxjaywe4czhnm

Systems Approaches to Sustainable Advancement of Developing Countries: Recent Contributions

Mile Stankovski, Leyla Goren, Tatyana Kolemisevska-Gugulovska, Georgi Dimirovski
2008 IFAC Proceedings Volumes  
Recent developments have put new emphasis on the IFAC activities dedicated to help improving the technological background of developing countries so as to assists their sustainable but accelerated developments  ...  within the more and more globalized economy hence a decisive role in ameliorating current socioeconomic problems in developing countries.  ...  The 2001 workshop in Ohrid contributed as plenary talks: aviation infrastructure in developing countries; neural-network orbit prediction for a geostationary satellite; and control incentives for a leader-follower  ... 
doi:10.3182/20080706-5-kr-1001.00884 fatcat:dghbsggkobcv5gzuqihyp6ntiq
« Previous Showing results 1 — 15 out of 1,817 results