Filters








31 Hits in 3.4 sec

Nested-Wasserstein Self-Imitation Learning for Sequence Generation [article]

Ruiyi Zhang, Changyou Chen, Zhe Gan, Zheng Wen, Wenlin Wang, Lawrence Carin
2020 arXiv   pre-print
To further exploit it, a novel nested-Wasserstein self-imitation learning framework is developed, encouraging the model to exploit historical high-rewarded sequences for enhanced exploration and better  ...  Reinforcement learning (RL) has been widely studied for improving sequence-generation models.  ...  Acknowledge The authors would like to thank the anonymous reviewers for their insightful comments. The research was supported in part by DARPA, DOE, NIH, NSF and ONR.  ... 
arXiv:2001.06944v1 fatcat:bcdhqcnwhba6feyf455ncgw27q

Simplicial and Topological Descriptions of Human Brain Dynamics

Jacob Billings, Manish Saggar, Jaroslav Hlinka, Shella Keilholz, Giovanni Petri
2021 Network Neuroscience  
Whereas brain imaging tools like functional Magnetic Resonance Imaging (fMRI) afford measurements of whole-brain activity, it remains unclear how best to interpret patterns found amid the data's apparent self-organization  ...  SUPPORTING INFORMATION Supporting information for this article is available at https://doi.org/10.1162/netn_a_00190. AUTHOR CONTRIBUTIONS  ...  multiscale self-organization.  ... 
doi:10.1162/netn_a_00190 pmid:34189377 pmcid:PMC8233107 fatcat:nqyi4sxx3vcj5dir7ahdy2dloq

Deep Learning for Free-Hand Sketch: A Survey [article]

Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang
2022 arXiv   pre-print
(iii) Promotion of future work via a discussion of bottlenecks, open problems, and potential research directions for the community.  ...  The progress of deep learning has immensely benefited free-hand sketch research and applications.  ...  Discussion Current issues in SBIR include: Self-supervised pre-training for SBIR [115] , [239] , optimizing SBIR for early retrieval using partially drawn sketches, for example using reinforcement learning  ... 
arXiv:2001.02600v3 fatcat:lek5sivzsrat3i52lqh2eifnia

A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning [article]

Xuan Di, Rongye Shi
2020 arXiv   pre-print
Models used for each phase are summarized, encompassing game theory, deep (reinforcement) learning, and imitation learning.  ...  It is the first-of-its-kind survey paper to comprehensively review literature in both transportation engineering and AI for mixed traffic modeling.  ...  Acknowledgments The authors would like to thank Data Science Institute from Columbia University for providing a seed grant for this research.  ... 
arXiv:2007.05156v1 fatcat:6pr3en5opfguje77wpa4dwr6pi

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.  ...  At the end of this paper, we conclude the further development of BMs in a more general view.  ...  Self-supervised Learning Theory Self-Supervised Learning (SSL) emerges to be a promising paradigm for learning data representations without labeled data.  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

Synthetic Data for Deep Learning [article]

Sergey I. Nikolenko
2019 arXiv   pre-print
Synthetic data is an increasingly popular tool for training deep learning models, especially in computer vision but also in other areas.  ...  Third, we turn to privacy-related applications of synthetic data and review the work on generating synthetic datasets with differential privacy guarantees.  ...  Another direction where synthetic data might be useful for learning control is to generate synthetic behaviours to improve imitation learning [433] . Bansal et al.  ... 
arXiv:1909.11512v1 fatcat:qquxnw4dfvgmfeztbpdqhr44gy

A comprehensive review on convolutional neural network in machine fault diagnosis [article]

Jinyang Jiao, Ming Zhao, Jing Lin, Kaixuan Liang
2020 arXiv   pre-print
Generally, a typical CNFD framework is composed of the following steps, namely, data collection, model construction, and feature learning and decision making, thus this paper is organized by following  ...  However, there has not been a systematic review to cover these studies and make a prospect for the further research.  ...  machine fault diagnosis are the original 2-D structure by imitating the image processing.  ... 
arXiv:2002.07605v1 fatcat:54w3panr35bb7app4y7dfnjeqa

Deep Learning in Science [article]

Stefano Bianchini, Moritz Müller, Pierre Pelletier
2020 arXiv   pre-print
However, the 'DL principle' qualifies for its versatility as the nucleus of a general scientific method that advances science in a measurable way.  ...  Much of the recent success of Artificial Intelligence (AI) has been spurred on by impressive achievements within a broader family of machine learning methods, commonly referred to as Deep Learning (DL)  ...  adversarial evolutionary algorithms link prediction graph laplacian imitation learning latent variables dna sequences homomorphic encryption experimental results lower bound image retrieval  ... 
arXiv:2009.01575v2 fatcat:4ttqgjdjfjbydp7flnhcgg5p7m

Improving Adversarial Text Generation by Modeling the Distant Future [article]

Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Dinghan Shen, Guoyin Wang, Zheng Wen, Lawrence Carin
2020 arXiv   pre-print
We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues.  ...  Specifically, we propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization  ...  Acknowledgement The authors would like to thank the anonymous reviewers for their insightful comments. The research was supported in part by DARPA, DOE, NIH, NSF and ONR.  ... 
arXiv:2005.01279v1 fatcat:txiqigbiqfe57k5mednpv25qvi

Final Program, The 2012 International Neuropsychological Society Mid-Year Meeting/11th Nordic Meeting in Neuropsychology June 27–30, 2012 Oslo, Norway

2012 Journal of the International Neuropsychological Society  
WASSERSTEIN. Adult ADHD -a Multifaceted Approach to Assessment and Intervention.  ...  Objective: The study was part of the Learning to Learn -project that developed services for adults with learning disabilities.  ...  ., 2000), a cellular model for learning and memory.  ... 
doi:10.1017/s1355617712001063 fatcat:hvqdxc6a5jb6rfbhapoem4q72i

Forecasting: theory and practice [article]

Fotios Petropoulos, Daniele Apiletti, Vassilios Assimakopoulos, Mohamed Zied Babai, Devon K. Barrow, Souhaib Ben Taieb, Christoph Bergmeir, Ricardo J. Bessa, Jakub Bijak, John E. Boylan, Jethro Browell, Claudio Carnevale (+68 others)
2022 arXiv   pre-print
However, we wish that our encyclopedic presentation will offer a point of reference for the rich work that has been undertaken over the last decades, with some key insights for the future of forecasting  ...  The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges.  ...  first, and the imitators, adopting at a later stage by imitating others' behaviour and thus responsible for word-of-mouth dynamics.  ... 
arXiv:2012.03854v4 fatcat:p32c67sy65cfdejq7ndfs3g7dm

An Introduction to Jacob Boehme: Four Centuries of Thought and Reception

Geoffrey Rowell
2014 International Journal for the Study of the Christian Church  
Acknowledgments Mutual in one anothers love and wrath all renewing We live as One Man; for contracting our infi nite senses We behold multitude; or expanding: we behold as one, As One Man all the Universal  ...  The lay and the learned are integrated into a sweeping eschatological perspective and insinuated into the sequence of the seven qualities in nature.  ...  The young poet Heinrich has to learn that the "true" spirit of his deepest self is simultaneously the true spirit of the cosmos.  ... 
doi:10.1080/1474225x.2014.883562 fatcat:s4dplq6khba6re7d3yj7kuux4a

Deep Learning for Software Security

VAN KHAC NGUYEN
2021
Although there have been significant research efforts developed for SV detection, there are several challenges that current methods fail to address: i) transferring the learning on SVs from label-rich  ...  software projects to unlabelled ones, ii) detecting SVs at a fine-grained level, iii) detecting coherent segments of functions for detecting SVs.  ...  The internal gaps in general might contain data, jump tables or instructions from other functions (e.g., nested functions).  ... 
doi:10.26180/13728244 fatcat:ad2nhsocpbgafmjjnoahrwirc4

Astronomy and Literature | Canon and Stylometrics

Dale Kedwards, Tom McLeish, Mary Garrison, Divna Manolova, Victoria Flood, Matthew Francis, Jeroen Deploige, Jeroen De Gussem, Mary Dockray-Miller, Michael D.C. Drout, Sarah Kinkade, Jillian Valerio (+3 others)
2021 Interfaces: A Journal of Medieval European Literatures  
Undoubtedly, Hildegard's style was imitated at the Rupertsberg, where multiple of her assistants had been in the front row in learning to imitate and conjure up the visionary's style.  ...  Do they indicate, for instance, that already during her life, Hildegard was consciously constructing her self-image for posterity?  ...  In general, it is possible to conclude that the diversity was considerable and specific conventions for particular times, plac- es and even for each manuscript were normal.  ... 
doi:10.54103/interfaces-08-01 fatcat:omqbrh5wvrajhcusiqjufq4swq

Woody on rye: Jewishness in the films and plays of Woody Allen

2014 ChoiceReviews  
On a very general level, Allen's film does imitate action, a serious and complete one at that, and it certainly does have a neat structure.  ...  Allen is one of a generation of Jewish comic writers and performers -including Neil Simon, Mel Brooks, Jackie Mason, Elaine May, Wendy Wasserstein, and others -who have had their work dismissed as extensions  ... 
doi:10.5860/choice.52-0191 fatcat:ciwqtf7bhbgfjc3cm55zjcjh2m
« Previous Showing results 1 — 15 out of 31 results