Filters








27,514 Hits in 8.4 sec

Automatic Data Augmentation for Generalization in Deep Reinforcement Learning [article]

Roberta Raileanu, Max Goldstein, Denis Yarats, Ilya Kostrikov, Rob Fergus
2021 arXiv   pre-print
In this paper, we compare three approaches for automatically finding an appropriate augmentation.  ...  Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments.  ...  Introduction Generalization to new environments remains a major challenge in deep reinforcement learning (RL).  ... 
arXiv:2006.12862v2 fatcat:cbrw6bas4rajdf2usv3tqlslha

Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation [article]

Tiexin Qin and Ziyuan Wang and Kelei He and Yinghuan Shi and Yang Gao and Dinggang Shen
2020 arXiv   pre-print
In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement  ...  Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation  ...  Regarding this challenge, we in this paper present a learning-based automatic data augmentation method for medical image segmentation, which introduces the deep reinforcement learning (DRL) to explore  ... 
arXiv:2002.09703v1 fatcat:ilt6yxnybndwnlqrs5t4sygete

Automatic Data Augmentation by Learning the Deterministic Policy [article]

Yinghuan Shi, Tiexin Qin, Yong Liu, Jiwen Lu, Yang Gao, Dinggang Shen
2019 arXiv   pre-print
Aiming to produce sufficient and diverse training samples, data augmentation has been demonstrated for its effectiveness in training deep models.  ...  Specifically, the current augmented subset is required to maximize the performance improvement compared with the last augmented subset by learning the deterministic augmentation policy using deep reinforcement  ...  Also, we will exploit the different action selection preferences in different datasets to guide better action design and initialization.  ... 
arXiv:1910.08343v2 fatcat:kbmxddhnqbca3efmmcbs7rrnx4

Reinforcement Evolutionary Learning Method for self-learning [article]

Kumarjit Pathak, Jitin Kapila
2018 arXiv   pre-print
Quantitative research is the most widely spread application of data science in Marketing or financial domain where applicability of state of the art reinforcement learning for auto-learning is less explored  ...  Our proposed solution is a reinforcement learning based, true self-learning algorithm which can adapt to the data change or concept drift and auto learn and self-calibrate for the new patterns of the data  ...  Data sample generator is used to generate sample for current learned data points for the algorithm so that the old learning is not forgotten by the network.  ... 
arXiv:1810.03198v1 fatcat:xdrufyoocbe5ji34pdbdvcn52y

Deep Learning – A first Meta-Survey of selected Reviews across Scientific Disciplines and their Research Impact [article]

Jan Egger, Antonio Pepe, Christina Gsaxner, Jianning Li
2020 arXiv   pre-print
However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks  ...  For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides over 11 000 results for the search term 'deep learning' in Q3 2020, and 90 are  ...  Data augmentation Data augmentation can be used for the expansion of (limited) datasets to obtain larger training and evaluation sets.  ... 
arXiv:2011.08184v1 fatcat:7eofypvqordn7i4o7qmtoaaydi

Sampling Strategies for GAN Synthetic Data [article]

Binod Bhattarai, Seungryul Baek, Rumeysa Bodur, Tae-Kyun Kim
2019 arXiv   pre-print
This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs).  ...  In addition to this, we explore reinforcement learning (RL) to automatically search a subset of meaningful synthetic examples from a large pool of GAN synthetic data.  ...  Please note that our methods are generic and can be applied for VAEs synthetic data too. Reinforcement Learning.  ... 
arXiv:1909.04689v1 fatcat:q5rqagm5ere5hm2stqmlaqienq

Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation [article]

Hanping Zhang, Yuhong Guo
2021 arXiv   pre-print
In this work, we propose a novel policy-aware adversarial data augmentation method to augment the standard policy learning method with automatically generated trajectory data.  ...  The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments.  ...  In recent studies, some broadly applied data augmentation approaches in deep learning have been brought into reinforcement learning. Cobbe et al.  ... 
arXiv:2106.15587v2 fatcat:5emc4oswtzf27e3yjn6l5hj6nq

Deep Reinforcement Learning with Mixed Convolutional Network [article]

Yanyu Zhang
2020 arXiv   pre-print
The dataset is generated by playing the game manually in Gym and used a data augmentation method to expand the dataset to 4 times larger than before.  ...  This paper presents a convolutional neural network (CNN) to playing the CarRacing-v0 using imitation learning in OpenAI Gym.  ...  Introduction OpenAI Gym is a popular open-source repository of reinforcement learning (RL) ( [5] [8] ) environments and development tools.  ... 
arXiv:2010.00717v2 fatcat:4aecue2qfzgstea5up763e73iu

Automatic Data Augmentation for 3D Medical Image Segmentation [article]

Ju Xu, Mengzhang Li, Zhanxing Zhu
2020 arXiv   pre-print
Data augmentation is an effective and universal technique for improving generalization performance of deep neural networks.  ...  To fully exploit the potential of data augmentation, we propose an efficient algorithm to automatically search for the optimal augmentation strategies.  ...  In [16] , the authors proposed to utilize reinforcement learning to search for augmentation strategies.  ... 
arXiv:2010.11695v2 fatcat:6d4ov4hhdngijbbpyvtmjm3eyi

Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net

Mizuho Nishio, Shunjiro Noguchi, Koji Fujimoto
2020 Applied Sciences  
Combinations of data augmentation methods and deep learning architectures for automatic pancreas segmentation on CT images are proposed and evaluated.  ...  Ten combinations of the deep learning models and the data augmentation methods were evaluated.  ...  For this purpose, AutoAugment finds the best combination of data augmentation [18] . However, it is computationally expensive due to its use of reinforcement learning.  ... 
doi:10.3390/app10103360 fatcat:3qv6qaaxcra7nf65cyr76c57la

Time Series Data Augmentation for Deep Learning: A Survey [article]

Qingsong Wen, Liang Sun, Fan Yang, Xiaomin Song, Jingkun Gao, Xue Wang, Huan Xu
2021 arXiv   pre-print
In this paper, we systematically review different data augmentation methods for time series.  ...  As an effective way to enhance the size and quality of the training data, data augmentation is crucial to the successful application of deep learning models on time series data.  ...  Automated Data Augmentation The idea of automated data augmentation is to automatically search for optimal data augmentation policies through reinforcement learning, meta learning, or evolutionary search  ... 
arXiv:2002.12478v2 fatcat:rhyj67nrgje5pg66wmxg5qhyge

Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation [article]

Dong Yang, Holger Roth, Ziyue Xu, Fausto Milletari, Ling Zhang, Daguang Xu
2020 arXiv   pre-print
The proposed approach can be utilized for tuning hyper-parameters, and selecting necessary data augmentation with certain probabilities.  ...  Nevertheless, to fully exploit the potentials of neural networks, we propose an automated searching approach for the optimal training strategy with reinforcement learning.  ...  In this work, we propose a reinforcement learning-based approach to search the best training strategy of deep neural networks for a specific 3D medical image segmentation task.  ... 
arXiv:2006.05847v1 fatcat:zzy3jm7y2ncbngxwpwwejcu2je

Automatically Designing CNN Architectures for Medical Image Segmentation [chapter]

Aliasghar Mortazi, Ulas Bagci
2018 Lecture Notes in Computer Science  
Our proposed method is based on a policy gradient reinforcement learning for which the reward function is assigned a segmentation evaluation utility (i.e., dice index).  ...  To address this tedious problem, we propose a novel algorithm to optimally find hyperparameters of a deep network architecture automatically.  ...  Our architecture design was fully automatic and based on policy gradient reinforcement learning.  ... 
doi:10.1007/978-3-030-00919-9_12 fatcat:vdohu3hj2jcvzef262u7ll5cj4

Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

Danshi Wang, Min Zhang
2021 Frontiers in Communications and Networks  
Additionally, a generative adversarial network (GAN) is introduced for data augmentation to expand the training dataset from rare experimental data.  ...  Finally, deep reinforcement learning (DRL) is applied to perform self-configuration and adaptive allocation for optical networks.  ...  MZ focused on reinforcement learning-related research.  ... 
doi:10.3389/frcmn.2021.656786 fatcat:bhoisltoxjbuvddl6zykab3764

Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning [article]

Md Masudur Rahman, Yexiang Xue
2022 arXiv   pre-print
Deep Reinforcement Learning (RL) agents often overfit the training environment, leading to poor generalization performance.  ...  Experimental results reveal that Thinker leads to better generalization capability in the Procgen benchmark environments compared to base algorithms and several data augmentation techniques.  ...  Introduction Deep reinforcement learning has achieved tremendous success.  ... 
arXiv:2207.07749v1 fatcat:fsu7pgaywvdctiwglswvlyq6ha
« Previous Showing results 1 — 15 out of 27,514 results