250 Hits in 13.6 sec

Universal Approximation Theorems for Differentiable Geometric Deep Learning [article]

Anastasis Kratsios, Leonie Papon
2022 arXiv   pre-print
This paper addresses the growing need to process non-Euclidean data, by introducing a geometric deep learning (GDL) framework for building universal feedforward-type models compatible with differentiable  ...  In the Euclidean setting, our results imply a quantitative version of Kidger and Lyons (2020)'s approximation theorem and a data-dependent version of Yarotsky and Zhevnerchuk (2019)'s uncursed approximation  ...  We grateful to Patrick Kidger for his helpful insights and encouragement.  ... 
arXiv:2101.05390v4 fatcat:dgbgiv7ymrbttapiwlgiizrtaa

Optical Communication in Space: Challenges and Mitigation Techniques

Hemani Kaushal, Georges Kaddoum
2017 IEEE Communications Surveys and Tutorials  
The latter part of the paper will provide the reader with an exhaustive review of various techniques both at physical layer as well as at the other layers i.e., link, network or transport layer to combat  ...  In recent years, free space optical communication has gained significant importance owing to its unique features: large bandwidth, license-free spectrum, high data rate, easy and quick deployability, less  ...  forward control, and neural network [328] .  ... 
doi:10.1109/comst.2016.2603518 fatcat:zv3fa7k2pbet3pi6gphq6izqae


2021 2021 National Conference on Communications (NCC)  
Nonetheless, not every problem can and should be solved using deep neural networks (DNNs).  ...  The following part of the tutorial will cover the fundamentals of radar detection with a focus on the ubiquitous Neyman-Pearson detection rule, the likelihood ratio test and the constant false alarm rate  ...  We show that for the optimal approximate AoI, server utilization (ratio of arrival rate and service rate) for each server should be same as the optimal server utilization with a single server queue.  ... 
doi:10.1109/ncc52529.2021.9530194 fatcat:ahdw5ezvtrh4nb47l2qeos3dwq

Evolution of novel activation functions in neural network training for astronomy data: habitability classification of exoplanets

Snehanshu Saha, Nithin Nagaraj, Archana Mathur, Rahul Yedida, Sneha H R
2020 The European Physical Journal Special Topics  
Finally, the activation functions have been implemented in plain vanilla feed-forward neural network to classify exoplanets.  ...  The theory of ordinary differential equations and fixed point are exploited to justify the "lack of tuning efforts" to achieve optimal performance compared to traditional activation functions.  ...  Thus, SBAF can be used with a feed-forward network with a single hidden layer containing a finite number of neurons to approximate a wide variety of linear and non-linear functions.  ... 
doi:10.1140/epjst/e2020-000098-9 pmid:33194093 pmcid:PMC7651829 fatcat:ea3rnndkpvffbhigw3s7yfkyjm

Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation [article]

Ali Hatamizadeh
2020 arXiv   pre-print
Image segmentation is a fundamental and challenging problem in computer vision with applications spanning multiple areas, such as medical imaging, remote sensing, and autonomous vehicles.  ...  that unifies CNNs and active contour models with learnable parameters for fast and robust object delineation, (3) a novel approach for disentangling edge and texture processing in segmentation networks  ...  assessment and quantification of chronic obstructive pulmonary diseases (COPD) and interstitial lung diseases (ILD), by narrowing down the search space to the lung lobes most-likely to be affected.  ... 
arXiv:2006.12706v1 fatcat:6jchhrv6zrhlhbpcak6fcbh4a4

27th Annual Computational Neuroscience Meeting (CNS*2018): Part One

2018 BMC Neuroscience  
All network simulations carried out with NEST (http:// www.nest-simul  ...  Acknowledgements This work has been supported by the Creative Unit I-See of the University of Bremen and the BMBF, Bernstein Award Udo Ernst, Grant No. 01GQ1106.  ...  In addition, INa inactivates more than in models with weak feed forward coupling.  ... 
doi:10.1186/s12868-018-0452-x pmid:30373544 pmcid:PMC6205781 fatcat:xv7pgbp76zbdfksl545xof2vzy

Engineering, Technology & Applied Science Research (ETASR), Vol. 12, No. 1, pp. 7974-8227

2022 Zenodo  
ISSN: 1792-8036 and 2241-4487.  ...  of science application, technology, and engineering.  ...  Kotzampigikis from the Department of Electrical and Computer Engineering of the University of Peloponnese, in the repetitive task of joining different line parts in order to comply with Google My Maps  ... 
doi:10.5281/zenodo.6369694 fatcat:nvdnhvh53rcvhiic5lij7azjka

CARS 2020—Computer Assisted Radiology and Surgery Proceedings of the 34th International Congress and Exhibition, Munich, Germany, June 23–27, 2020

2020 International Journal of Computer Assisted Radiology and Surgery  
A hybrid (analogue and digital) CARS 2020 has therefore been envisaged to take place at the University Hospital in Munich, with a balanced combination of analogue/personal and digital presentations and  ...  In the times of COVID-19 overshadowing CARS 2020 and what the future may hold, a CARS meeting with these numbers of participants is not feasible anymore and new ways have to be explored to still fulfill  ...  Acknowledgements We would like to gratefully thank members in Image-Lab, department of Radiology, the University of Tokyo Hospital. We also thank Dr. Kimura and Dr.  ... 
doi:10.1007/s11548-020-02171-6 pmid:32514840 fatcat:lyhdb2zfpjcqbf4mmbunddwroq

Tracking linguistic primitives [chapter]

Niklas Johansson
2017 Iconicity in Language and Literature  
FATHER, a three-way deictic distinction between I, indicatory deictic concepts and THERE, and a dimensional tripartite oppositional relationship between Small and (possibly with Intense Vision-Touch),  ...  This thesis investigates how cross-linguistic phoneme distributions of 56 fundamental oppositional concepts can reveal semantic relationships by looking into the linguistic forms of 75 genetically and  ...  Relating to this the phenomenon of phonosemantics is presented as an universal factor of language and its close connection to fundamental vocabulary.  ... 
doi:10.1075/ill.15.03joh fatcat:u6dlhusmwvf6jpfjlgifqntye4

EMG-based Simultaneous and Proportional Estimation of Wrist Kinematics and its Application in Intuitive Myoelectric Control for Unilateral transradial Amputees

Farina Dario
2011 Frontiers in Computational Neuroscience  
All network simulations were carried out with NEST (  ...  Popovic 1,2,3* and Stefan Lang 1,3 Acknowledgements We would like to thank Professor Neil Burgess for our illuminating discussions with him.  ...  We present feed-forward artificial neural networks (ANNs) that quantitatively predict the phonotactic value for untested calling songs that are described by temporal features such as duration, pause, period  ... 
doi:10.3389/conf.fncom.2011.53.00081 fatcat:nkq5wesfpbcjnikbxqh3v3gtqi

CARS 2021: Computer Assisted Radiology and Surgery Proceedings of the 35th International Congress and Exhibition Munich, Germany, June 21–25, 2021

2021 International Journal of Computer Assisted Radiology and Surgery  
The University Rovira i Virgili also supports this work with project 2019PFR-B2-61. References  ...  For the first step of approximating depth maps, three deep neural networks with different architectures, namely ''V-Net'', ''U-Net'', and ''modified U-Net'' (with a ResNet encoder) were constructed and  ...  Finally, we train the whole network with a learning rate of 0.00001 for 50 epochs combined to an early stopping condition.  ... 
doi:10.1007/s11548-021-02375-4 pmid:34085172 fatcat:6d564hsv2fbybkhw4wvc7uuxcy

Patterns, predictions, and actions: A story about machine learning [article]

Moritz Hardt, Benjamin Recht
2021 arXiv   pre-print
Self-contained introductions to causality, the practice of causal inference, sequential decision making, and reinforcement learning equip the reader with concepts and tools to reason about actions and  ...  Throughout, the text discusses historical context and societal impact. We invite readers from all backgrounds; some experience with probability, calculus, and linear algebra suffices.  ...  Such networks are no longer universal approximators, but they are non-convex parameterizations of linear functions.  ... 
arXiv:2102.05242v2 fatcat:wy47g4fojnfuxngklyewtjtqdi

A method of characterizing radio signal space for wireless device localization

John-Austen Francisco, Richard P. Martin
2015 Tsinghua Science and Technology  
The DDLHM is designed to characterize the type and degree of signal distortion relative to lognormal signal-to-distance path models.  ...  Using only 4% of the maximal set of DDLHMs, we found the reduced set matches with an acceptable degree of error 95% of the time.  ...  Understanding how expected RSSI varies spatially is fundamental to indoor wireless data networking beyond positioning, and is critical 386 Tsinghua Science and Technology, August 2015, 20 (4) : when  ... 
doi:10.1109/tst.2015.7173454 fatcat:q6fianw5ajcmrpns3jto6gy3gu

Engineering, Technology & Applied Science Research (ETASR), Vol. 11, No. 2, pp. 6845-7068 [article]

2021 Zenodo  
ISSN: 1792-8036 and 2241-4487.  ...  of science application, technology, and engineering.  ...  ACKNOWLEDGMENT The authors are grateful to the Institute for Research and Development, Suan Sunandha Rajabhat University and the Faculty of Science at Ubon Ratchathani University, for supporting this research  ... 
doi:10.5281/zenodo.4720665 fatcat:mk2prflstjaa3bhkjenwy22s6u

Nonlinear acoustics of water‐saturated marine sediments

Leif Bjørnø
1976 Journal of the Acoustical Society of America  
Results from an acoustic sounder network study of the This study, begun in 1974, was expanded to a small network of three stations in 1975, with some additional data received from two sites operated by  ...  Echograms obtained up to May 1976 (operational period of approximately 1500 h) have been qualitatively analyzed with respect telheir structural details.  ...  In a prelimin•.ry experiment, fundamental frequency was found to vary with subglottal pressure at average rates of 3--5 Hz/cm HzO.  ... 
doi:10.1121/1.2003625 fatcat:xzwtedhhn5b2rfurl3f246z6m4
« Previous Showing results 1 — 15 out of 250 results