Filters








658,561 Hits in 5.5 sec

The science of deep learning

Richard Baraniuk, David Donoho, Matan Gavish
2020 Proceedings of the National Academy of Sciences of the United States of America  
artificial intelligence | machine learning | deep learning | neural networks www.pnas.org/cgi/  ...  Acknowledgments The authors thank Dame Jillian Sackler for her many years of sponsorship of National Academy of Sciences Sackler Colloquia.  ...  Many graduate students came to Washington, DC from around the United States to participate actively. The National Academy of Sciences and PNAS staff have also been very helpful at every stage.  ... 
doi:10.1073/pnas.2020596117 pmid:33229565 fatcat:hf4io3euobaungvigwvp2nzkpq

Reproducible Science of Deep Learning: The Pruning Case Study [article]

Michela Paganini
2020 figshare.com  
facilitated the investigation of the behavior of pruned models.  ...  I will highlight examples such as the contribution of centralized, reusable pruning methods in PyTorch and the open-sourcing of the 'dagger' framework for reproducible and reusable experiment orchestration  ...  Measurements are affected by sources of variations What can we learn from the other sciences? 2.  ... 
doi:10.6084/m9.figshare.12991199.v1 fatcat:jcdl6v64czezdaem4ujaizwmgu

The Role of Citizen Science and Deep Learning in Camera Trapping

Matyáš Adam, Pavel Tomášek, Jiří Lehejček, Jakub Trojan, Tomáš Jůnek
2021 Sustainability  
Our approach aims to show a new perspective and to update the recent progress in engaging the enthusiasm of citizen scientists and in including machine learning processes into image classification in camera  ...  This approach (combining machine learning and the input from citizen scientists) may significantly assist in streamlining the processing of camera trap data while simultaneously raising public environmental  ...  Our thanks also go to Steve Ridgill and the second native speaker for the English improvements of the text. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/su131810287 fatcat:xa7nvzd47vbhjc4wgtysv4azui

Special Issue on the Mathematical Foundations of Deep Learning in Imaging Science

Joan Bruna, Eldad Haber, Gitta Kutyniok, Thomas Pock, René Vidal
2020 Journal of Mathematical Imaging and Vision  
Many mathematically inclined researchers have a strong desire to understand the theoretical reasons for the success of these approaches and to find relations between deep learning and mathematically well-established  ...  Deep learning methods have become an omnipresent and highly successful part of recent approaches in imaging and vision.  ...  deep learning.  ... 
doi:10.1007/s10851-020-00955-8 fatcat:n5kayejz4fcxxk5dvfit3gsbru

Deep Learning by Doing: The NVIDIA Deep Learning Institute and University Ambassador Program

Xi Chen, Gregory S. Gutmann
2019 The Journal of Computational Science Education  
, and engineers solve real-world problems in a wide range of domains using deep learning and accelerated computing.  ...  Advanced and domain-specific courses in deep learning are also available.  ...  ACKNOWLEDGMENTS The authors would like to thank NVIDIA Deep Learning Institute for providing the figures, documents and online course platform, and Tokyo Institute of Technology and ACM University of Kentucky  ... 
doi:10.22369/issn.2153-4136/10/1/16 fatcat:zb5mfkg2aza6dar6gdzj2zfqxq

Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences

Igor Ryazanov, Amanda T. Nylund, Debabrota Basu, Ida-Maja Hassellöv, Alexander Schliep
2021 Journal of Marine Science and Engineering  
Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science.  ...  Its advantages are demonstrated with our novel deep learning-based expert-in-the-loop framework for automatic detection of turbulent wake signatures in echo sounder data.  ...  The framework also serves as a demonstration of general applicability of the deep learning approach in marine sciences.  ... 
doi:10.3390/jmse9020169 fatcat:3y2oviaj7nckdfy5stmybqasti

Deep Loving - The Friend of Deep Learning

Satish Gajawada, Hassan M. H. Mustafa
2020 Global Journal of Computer Science and Technology  
The definition of Deep Learning is shown followed by a literature review of the "Deep Loving" field.  ...  In this article, we coin the term "Deep Loving". After the publication of this article, "Deep Loving" will be considered as the friend of Deep Learning.  ...  Acknowledgments Thanks to Very Excellent Editorial Team of "Global Journal of Computer Science and Technology (GJCST)" and reviewers for accepting our innovative invention titled "Deep Loving."  ... 
doi:10.34257/gjcstdvol20is1pg51 fatcat:bwx77ssllvhajn7aegy5i3c4ve

Deep learning in deep time

Alexander E. White
2020 Proceedings of the National Academy of Sciences of the United States of America  
The crux of the authors' approach is the combination of recently developed high-resolution microscope technology (11) with deep convolutional neural networks (CNNs), powerful machine-learning models developed  ...  Romero et al. (9) show how this record can be further refined with deep learning.  ...  science of deep learning.  ... 
doi:10.1073/pnas.2020870117 pmid:33168754 fatcat:3eff66s32fedtm3d5av5jkm62u

Are There Deep Reasons Underlying the Pathologies of Today's Deep Learning Algorithms? [chapter]

Ben Goertzel
2015 Lecture Notes in Computer Science  
It is hypothesized that these behaviors are tied with limitations in the internal representations learned by these architectures, and that these same limitations would inhibit integration of these architectures  ...  Some currently popular and successful deep learning architectures display certain pathological behaviors (e.g. confidently classifying random data as belonging to a familiar category of nonrandom images  ...  Broad and Narrow Interpretations of "Deep Learning" In his book"Deep Learning" [11] , cognitive scientist Stellan Ohlson formulates the concept of deep learning as a general set of information-processing  ... 
doi:10.1007/978-3-319-21365-1_8 fatcat:drynikjyujeetpdsgaa3xyxuym

Machine Learning and Deep Learning: Introduction and Applications

Tomoharu NAKASHIMA
2020 Journal of the Society of Materials Science Japan  
Furthermore, deep neural networks are explained as the extention to the three-layered neural networks. Finally, the application of the deep neural networks are shown with some examples.  ...  Most of the time, they refer machine learning when AI is discussed. This paper gives introduction to machine learning. First, the overview of the machine learning is given.  ...  · ⃗ x + w0} (4) (2) (4) 1 + exp{− ∑ i ⃗ w · ⃗ x + w0} | (5) 2 2 E E = 1 2 e 2 = 1 2 (y − yt) 2 (6) E E ⃗ w, w0 E (6) E 5 E w E w* 傾きが負のとき 傾きが正のとき ↗ w を増加させる ↘ w を減少させる E Fig. 5 Graphical illustration of  ... 
doi:10.2472/jsms.69.633 fatcat:mwos4cedsrfbvc3usnsuldrsmi

A REVIEW ON THE CONCEPT OF DEEP LEARNING

Shalini Bhaskar Bajaj
2020 International Journal of Innovative Research in Computer Science & Technology  
ANN is used by many online stores in the form of recommendation systems to offer suitable products based on their liking.  ...  In this work based on artificial neural network recurrent and convolutional network is proposed at the level of letters in order to classify and sort textual information with given classes.  ...  It was proposed for effective image recognition [1] by Yann LeCun and is a type of deep learning algorithm.  ... 
doi:10.21276/ijircst.2020.8.3.16 fatcat:xp6et5ukifgmbgvhq2nhsdsouu

The Design of Learning Activity in Flipped Classroom Based on Deep Learning Theory

YUNDUAN FANG
2017 DEStech Transactions on Social Science Education and Human Science  
of deep learning and surface learning.  ...  This paper puts forward the idea of transformation to the teaching design paradigm of the flipped classroom, designs the model of learning activity in flipped classroom based on deep learning theory.  ...  The purpose of deep learning is to practice, which is to solve the problem as the deep inquiry learning for the kernel, so it is the process of application and innovation of acquisition knowledge.  ... 
doi:10.12783/dtssehs/hsmet2017/16459 fatcat:t6wxgvdmlzdldprp5hy74l4jy4

Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory

Terrier
2020 Applied Sciences  
The results suggest that every person produces a unique trajectory of underfoot pressures while walking and that CNNs can learn the distinctive features of these trajectories.  ...  The best CNN classified a separate set containing 2,250 segments with an overall accuracy of 99.9%. A second set of 4,500 segments from the six remaining subjects was then used for transfer learning.  ...  Acknowledgments: The author gratefully thanks his daughter Laureline for proofreading the manuscript. Conflicts of Interest: The author declares no conflict of interest.  ... 
doi:10.3390/app10030774 fatcat:iumbfk22drawzfh65eaozfzbxy

The Experience of Deep Learning by Accounting Students

Martin Turner, Rachel F. Baskerville
2011 Social Science Research Network  
An implication of this study is the need to support accounting students to experience deep learning in first year courses to enable them to develop personal capabilities in their later university studies  ...  To do this, they need to experience deep learning. This study examines how to support accounting students to experience deep learning.  ...  Acknowledgements: We would like to acknowledge the valuable input and contribution of Professor Tom Angelo, La Trobe University.  ... 
doi:10.2139/ssrn.1912131 fatcat:kz56te2yxrcp7ikk2mojyp4lkm

Interactions Between Students and Tutor in Problem-Based Learning: The Significance of Deep Learning

Samy A. Azer
2009 Kaohsiung Journal of Medical Sciences  
ACKNOWLEDGMENTS The author would like to thank the President of the Kaohsiung Medical University, Professor Hsin-Su Yu, the Dean of the College of Medicine, Professor Chung-Sheng Lai, and Associate Dean  ...  , Professor Keh-Min Liu, for inviting him as a keynote speaker on this topic in the International Conference on Problem-Based Learning, which was held in Kaohsiung, Taiwan, in July 2008.  ...  The problems in the group are related to superficial learning (absence of deep learning).  ... 
doi:10.1016/s1607-551x(09)70068-3 pmid:19502144 fatcat:ibilfkpiafdkhaokxt3ffbzeom
« Previous Showing results 1 — 15 out of 658,561 results