Filters








24 Hits in 3.4 sec

Data-driven Regularization via Racecar Training for Generalizing Neural Networks [article]

You Xie, Nils Thuerey
2020 arXiv   pre-print
We propose a novel training approach for improving the generalization in neural networks.  ...  Despite being a surprisingly simple change, we demonstrate that this forward-backward training approach, which we refer to as racecar training, leads to significantly more generic features being extracted  ...  Supplemental Material for Data-driven Regularization via Racecar Training for Generalizing Neural Networks Below, we provide additional details regarding derivation, data sets, network architectures, and  ... 
arXiv:2007.00024v1 fatcat:yg3l7t75ajh57h5fwdxkhqzfhi

An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots [article]

Marcos V. Conde
2021 arXiv   pre-print
Part of the problem is to get a robot to emulate the perception of human beings, our sense of sight, replacing the eyes with cameras and the brain with mathematical models such as Neural Networks.  ...  techniques, Machine Learning, and various algorithms to make the robot understand the environment or scene, move, adapt its trajectory and perform its tasks (maintenance, exploration, etc.) without the need for  ...  Dropout [82] is simple, yet powerful regularization technique for neural networks.  ... 
arXiv:2112.05534v2 fatcat:3drhsxelvvdwvpsq5rvfpnukam

1/10th scale autonomous vehicle based on convolutional neural network

Avishkar Seth, Alice James*, Subhas C. Mukhopadhyay
2020 International Journal on Smart Sensing and Intelligent Systems  
This research paper shows a demonstration and implementation of an autonomous vehicle based on a convolutional neural network.  ...  The unique aspect of this project is the system design, the CAD modeling, and the track built used to train and test the self-driving capability of the car.  ...  In the next stage, these data are trained in a CNN (convolutional neural network) model on the host PC. The generated machine learning model is then transferred to the raspberry pi.  ... 
doi:10.21307/ijssis-2020-021 fatcat:ryxcshddtvaudevug764jioulu

Deep-Learning-Based Multivariate Pattern Analysis (dMVPA): A Tutorial and a Toolbox

Karl M Kuntzelman, Jacob M Williams, Phui Cheng Lim, Ashok Samal, Prahalada K Rao, Matthew R Johnson
2021 Frontiers in Human Neuroscience  
In a similar time frame, "deep learning" (a term for the use of artificial neural networks with convolutional, recurrent, or similarly sophisticated architectures) has produced a parallel revolution in  ...  In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data - which we term  ...  ACKNOWLEDGMENTS We thank Aaron Halvorsen and Hannah Ross for assistance with figure creation and manuscript editing.  ... 
doi:10.3389/fnhum.2021.638052 pmid:33737872 pmcid:PMC7960649 fatcat:h5jyzefvvvfghhhpec3wrmzjee

Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture [article]

Chinmay Vilas Samak, Tanmay Vilas Samak, Sivanathan Kandhasamy
2021 arXiv   pre-print
We adopted a hybrid imitation-reinforcement learning architecture and crafted a novel reward function to train a deep neural network policy to drive (using imitation learning) and race (using reinforcement  ...  In this work, we present a rigorous end-to-end control strategy for autonomous vehicles aimed at minimizing lap times in a time attack racing event.  ...  Imitation learning relies on a labeled dataset to learn the task of autonomous driving by training a deep neural network.  ... 
arXiv:2110.05437v1 fatcat:dpo5kmv37ra77dm2aw57q5hmhq

An Open-Source Scale Model Platform for Teaching Autonomous Vehicle Technologies

Bastien Vincke, Sergio Rodriguez Rodriguez Florez, Pascal Aubert
2021 Sensors  
Teaching the associated skills that are necessary for the analysis of such systems becomes a very difficult process and existing solutions do not facilitate learning.  ...  In this study, our efforts are devoted to proposingan open-source scale model vehicle platform that is designed for teaching the fundamental concepts of autonomous vehicles technologies that are adapted  ...  Figure 10 . 10 The object detector results deploying a pre-trained neural network model on-board the proposed scale-model vehicle prototype. Table 1 .  ... 
doi:10.3390/s21113850 fatcat:ya34grdytne7xcxkc4mizvq224

Real-time 3D Pose Estimation with a Monocular Camera Using Deep Learning and Object Priors On an Autonomous Racecar [article]

Ankit Dhall
2018 arXiv   pre-print
The network is trained for 250 epochs.  ...  Data for training and testing was initially acquired via smart-phone cameras, during the required lead time before procuring the Basler "ace" cameras.  ... 
arXiv:1809.10548v1 fatcat:5takrrvz5zfc3bjvkd3bvgbtaa

2020 Index IEEE Transactions on Vehicular Technology Vol. 69

2020 IEEE Transactions on Vehicular Technology  
Dec. 2020 16218-16223 Hoon-Kim, T., see Kumar, G., TVT July 2020 7707-7722 Horlin, F., see Monfared, S., TVT Oct. 2020 11369-11382 Horng, S., Lu, C., and Zhou, W., An Identity-Based and Revocable Data-Sharing  ...  + Check author entry for coauthors ami-mFading Channels With Integer and Non-Integerm; TVT March 2020 2785-2801 Hoang, T.M., Tran, X.N., Nguyen, B.C., and Dung, L.T., On the Performance of MIMO Full-Duplex  ...  ., +, TVT March 2020 2398-2410 Data-Driven Incipient Fault Detection and Diagnosis for the Running Gear in High-Speed Trains.  ... 
doi:10.1109/tvt.2021.3055470 fatcat:536l4pgnufhixneoa3a3dibdma

Rehabilitation Research at the National Institutes of Health

Walter R. Frontera, Jonathan F. Bean, Diane Damiano, Linda Ehrlich-Jones, Melanie Fried-Oken, Alan Jette, Ranu Jung, Rick L. Lieber, James F. Malec, Michael J. Mueller, Kenneth J. Ottenbacher, Keith E. Tansey (+1 others)
2017 American Journal of Physical Medicine & Rehabilitation  
scientists and the general public to comment on gaps in knowledge, opportunities for training, and infrastructure needs.  ...  main objectives of the Conference were to: 1) discuss the current NIH portfolio in rehabilitation research, 2) highlight advances in rehabilitation research supported by NIH, 3) provide an opportunity for  ...  Telerehab also offers the option for a holistic approach to patient care, for example, incorporating education, sensor data collection, and regular structured interactions with therapists.  ... 
doi:10.1097/phm.0000000000000700 pmid:28301426 pmcid:PMC5402894 fatcat:2qdlrrtfzjf6bn423cbfzr2z4m

Rehabilitation Research at the National Institutes of Health: Moving the Field Forward (Executive Summary)

Walter R. Frontera, Jonathan F. Bean, Diane Damiano, Linda Ehrlich-Jones, Melanie Fried-Oken, Alan Jette, Ranu Jung, Rick L. Lieber, James F. Malec, Michael J. Mueller, Kenneth J. Ottenbacher, Keith E. Tansey (+1 others)
2017 Archives of Physical Medicine and Rehabilitation  
Kennedy Shriver National Institute of Child Health and Human Development, the National Institute of Nursing Research, the National Institute of Biomedical Imaging and Bioengineering, the National Center for  ...  Telerehab also offers the option for a holistic approach to patient care-for example, incorporating education, sensor data collection, and regular structured interactions with therapists.  ...  Likewise, we must increase awareness and benefits of ATs for the general public.  ... 
doi:10.1016/j.apmr.2017.02.001 pmid:28343477 fatcat:pn7ari73oneb5i7c6v7dvtoaqq

Rehabilitation research at the National Institutes of Health: Moving the field forward (Executive Summary)

Walter R. Frontera, Jonathan F. Bean, Diane Damiano, Linda Ehrlich-Jones, Melanie Fried-Oken, Alan Jette, Ranu Jung, Rick L. Lieber, James F. Malec, Michael J. Mueller, Kenneth J. Ottenbacher, Keith E. Tansey (+1 others)
2017 Assistive technology  
Kennedy Shriver National Institute of Child Health and Human Development, the National Institute of Nursing Research, the National Institute of Biomedical Imaging and Bioengineering, the National Center for  ...  Telerehab also offers the option for a holistic approach to patient care-for example, incorporating education, sensor data collection, and regular structured interactions with therapists.  ...  Likewise, we must increase awareness and benefits of ATs for the general public.  ... 
doi:10.1080/10400435.2017.1306412 pmid:28617658 fatcat:7odg7uojnzeqlllltnj45orc3u

Rehabilitation research at the National Institutes of Health moving the field forward (executive summary)

Walter R. Frontera, Jonathan F. Bean, Diane Damiano, Linda Ehrlich-Jones, Melanie Fried-Oken, Alan Jette, Ranu Jung, Rick L. Lieber, James F. Malec, Michael J. Mueller, Kenneth J. Ottenbacher, Keith E. Tansey (+1 others)
2017 Rehabilitation Psychology  
Collaborative care approaches, including telecare, validated for pain and depression management, was considered a  ...  Kennedy Shriver National Institute of Child Health and Human Development, the National Institute of Nursing Research, the National Institute of Biomedical Imaging and Bioengineering, the National Center for  ...  scientists and the general public to comment on gaps in knowledge, opportunities for training, and infrastructure needs.  ... 
doi:10.1037/rep0000164 pmid:28682094 fatcat:o4qn6r2emrfnbpzoov7etoosh4

Rehabilitation Research at the National Institutes of Health: Moving the Field Forward (Executive Summary)

Walter R. Frontera, Jonathan F. Bean, Diane Damiano, Linda Ehrlich-Jones, Melanie Fried-Oken, Alan Jette, Ranu Jung, Rick L. Lieber, James F. Malec, Michael J. Mueller, Kenneth J. Ottenbacher, Keith E. Tansey (+1 others)
2017 American Journal of Occupational Therapy  
For decades, the National Institutes of Health (NIH) has been conducting and supporting research to discover new ways to minimize disability and enhance the quality of life of people with disabilities.  ...  After the passage of the Americans With Disabilities Act, NIH established the National Center for Medical Rehabilitation Research, with the goal of developing and implementing a rehabilitation research  ...  Kennedy Shriver National Institute of Child Health and Human Development, the National Institute of Nursing Research, the National Institute of Biomedical Imaging and Bioengineering, the National Center for  ... 
doi:10.5014/ajot.2017.713003 pmid:28422639 pmcid:PMC5397096 fatcat:rim3lxexvfgkppsdtgmncmprge

FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis [article]

Aman Sinha, Matthew O'Kelly, Hongrui Zheng, Rahul Mangharam, John Duchi, Russ Tedrake
2020 arXiv   pre-print
First, to generate a realistic, diverse set of opponents, we develop a novel method for self-play based on replica-exchange Markov chain Monte Carlo.  ...  robustness when approximating these computations in real-time motion-planning, and we demonstrate our methods experimentally on autonomous vehicles that achieve scaled speeds comparable to Formula One racecars  ...  These methods reweight training data to reduce the variance of the training loss [68] . While others apply DRO to episodic RL for training offline [82, 83] , we reweight the belief online.  ... 
arXiv:2003.03900v2 fatcat:xaxnxeensnhyliht7yrjti6amy

GP-RARS: evolving controllers for the Robot Auto Racing Simulator

Yehonatan Shichel, Moshe Sipper
2011 Memetic Computing  
We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator).  ...  Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of  ...  to create discrete input values for artificial neural networks.  ... 
doi:10.1007/s12293-011-0056-9 fatcat:urfynpznovfbbg6at3th6juxxe
« Previous Showing results 1 — 15 out of 24 results