Filters








63,514 Hits in 2.3 sec

A Deep Conditioning Treatment of Neural Networks [article]

Naman Agarwal and Pranjal Awasthi and Satyen Kale
2021 arXiv   pre-print
We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of the input data.  ...  As applications of these general results, we provide a generalization of the results of Das et al. (2019) showing that learnability of deep random neural networks with a large class of non-linear activations  ...  the question of whether depth helps in improving conditioning of the data, and as a result affecting optimization and generalization in deep neural networks.  ... 
arXiv:2002.01523v3 fatcat:vqey2c4crvauxhbtzq4renw7d4

Artificial Intelligence Based Insulin Sensitivity Prediction for Personalized Glycaemic Control in Intensive Care

Balázs Benyó, Béla Paláncz, Ákos Szlávecz, Bálint Szabó, Yahia Anane, Katalin Kovács, J. Geoffrey Chase
2020 IFAC-PapersOnLine  
The deep neural networks are trained by using three years of STAR treatment data. The methods are validated by comparing the prediction statistics with the reference data set.  ...  The deep neural networks are trained by using three years of STAR treatment data. The methods are validated by comparing the prediction statistics with the reference data set.  ...  K116574, by the BME-Biotechnology FIKP grant of EMMI (BME FIKP-BIO), by the EFOP-3.6.1-16-2016-00017 project, and by H2020 MSCA-RISE DCPM (#872488) grant.  ... 
doi:10.1016/j.ifacol.2020.12.659 fatcat:oto5dcyo2jbrfdust74pbpqub4

Deep Learning of Potential Outcomes [article]

Bernard Koch, Tim Sainburg, Pablo Geraldo, Song Jiang, Yizhou Sun, Jacob Gates Foster
2021 arXiv   pre-print
This review systematizes the emerging literature for causal inference using deep neural networks under the potential outcomes framework.  ...  The survey differs from other treatments of deep learning and causal inference in its sharp focus on observational causal estimation, its extended exposition of key algorithms, and its detailed tutorials  ...  A neural network with multiple hidden layers is called a "deep" network, hence the name "deep learning" (LeCun et al. 2015) .  ... 
arXiv:2110.04442v1 fatcat:kj3dfigqpjeo3j76ykmlephgdq

Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data [article]

Ning Liu and Ying Liu and Brent Logan and Zhiyuan Xu and Jian Tang and Yanzhi Wang
2018 arXiv   pre-print
Both steps depend on deep neural networks.  ...  The proposed DRL framework comprises (i) a supervised learning step to predict the most possible expert actions, and (ii) a deep reinforcement learning step to estimate the long-term value function of  ...  , fully-connected neural network as our deep neural network.  ... 
arXiv:1801.09271v1 fatcat:yvo76outz5cqhpnspapsrhp2yi

Deep Neural Networks for Estimation and Inference [article]

Max H. Farrell and Tengyuan Liang and Sanjog Misra
2019 arXiv   pre-print
We study deep neural networks and their use in semiparametric inference. We establish novel rates of convergence for deep feedforward neural nets.  ...  We demonstrate the effectiveness of deep learning with a Monte Carlo analysis and an empirical application to direct mail marketing.  ...  Neural Network Constructions For any loss, we estimate the target function using a deep ReLU network.  ... 
arXiv:1809.09953v3 fatcat:a5t7uwey4nc7nbidvtvu43ga6u

Pancreatic Cancer Survival Prediction: A Survey of the State-of-the-Art

Wilson Bakasa, Serestina Viriri, Huiling Chen
2021 Computational and Mathematical Methods in Medicine  
Because of bewildering and high volumes of data, the recent studies highlight the importance of machine learning (ML) algorithms like support vector machines and convolutional neural networks.  ...  Cancer early detection increases the chances of survival. Some cancer types, like pancreatic cancer, are challenging to diagnose or detect early, and the stages have a fast progression rate.  ...  Mask R-CNN [95] is a Faster R-CNNbased deep neural network that separates tumours in a processed image. This neural network performs segmentation and generates masks and bounding boxes.  ... 
doi:10.1155/2021/1188414 pmid:34630626 pmcid:PMC8497168 fatcat:3gwvh2gjlvd6plgpsnapafsjja

COVID-Net MLSys: Designing COVID-Net for the Clinical Workflow [article]

Audrey G. Chung, Maya Pavlova, Hayden Gunraj, Naomi Terhljan, Alexander MacLean, Hossein Aboutalebi, Siddharth Surana, Andy Zhao, Saad Abbasi, Alexander Wong
2021 arXiv   pre-print
The COVID-Net system is comprised of the continuously evolving COVIDx dataset, COVID-Net deep neural network for COVID-19 patient detection, and COVID-Net S deep neural networks for disease severity scoring  ...  The deep neural networks within the COVID-Net system possess state-of-the-art performance, and are designed to be integrated within a user interface (UI) for clinical decision support with automatic report  ...  COVID-Net S: Deep neural networks for disease severity scoring of COVID-19 positive patients The third core component in the COVID-Net system is the pair of COVID-Net S deep neural networks [21] , which  ... 
arXiv:2109.06421v1 fatcat:nbertmthgva2pjq7fcqjz7f6jq

Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data

Ying Liu, Brent Logan, Ning Liu, Zhiyuan Xu, Jian Tang, Yangzhi Wang
2017 2017 IEEE International Conference on Healthcare Informatics (ICHI)  
function of Dynamic Treatment Regimes.  ...  The proposed deep reinforcement learning framework contains a supervised learning step to predict the most possible expert actions; and a deep reinforcement learning step to estimate the long term value  ...  Three separate deep neural networks are developed for DTRs of initial conditioning (chemotherapy and prevention of GVHDs), treatment of acute and chronic GVHDs.  ... 
doi:10.1109/ichi.2017.45 pmid:29556119 pmcid:PMC5856473 dblp:conf/ichi/LiuLLXTW17 fatcat:vqezrv5urfbndca3l42lld7nia

Energy and Materials-Saving Management via Deep Learning for Wastewater Treatment Plants

Jianhui Wang, Keyi Wan, Xu Gao, Xuhong Cheng, Yu Shen, Zheng Wen, Usman Tariq, Md. Jalil Piran
2020 IEEE Access  
In this paper, a new hybrid neural network (PCA-CNN-LSTM) model based on deep neural network was proposed.  ...  Main contributions of this paper can be summarized as: 1) A new hybrid neural network (PCA-CNN-LSTM) model based on deep neural network was proposed.  ...  Bureau, with a cumulative research fund of more than 20 million yuan.  ... 
doi:10.1109/access.2020.3032531 fatcat:ktls4aobyjaobkgpzniaabl6ou

Deep Learning Model for Detection of Pain Intensity from Facial Expression [chapter]

Jeffrey Soar, Ghazal Bargshady, Xujuan Zhou, Frank Whittaker
2018 Lecture Notes in Computer Science  
The algorithm can extract and classify facial expression of pain among patients. In this paper, we propose a new deep learning model for detection of pain intensity from facial expressions.  ...  Many people who are suffering from a chronic pain face periods of acute pain and resulting problems during their illness and adequate reporting of symptoms is necessary for treatment.  ...  A deep neural network is usually represented as the composition of multiple nonlinear functions.  ... 
doi:10.1007/978-3-319-94523-1_22 fatcat:zhf2j4jquncalhactv4bnw7nhu

Deep Network Pharmacology: Targeting Glutamate Systems as Integrative Treatments for Jump-Starting Neural Networks and Recovery Trajectories

2021 Journal of Psychiatry and Brain Science  
Reframing our efforts with a view on integrative treatments that target core neural network function and plasticity may provide new approaches for lifting patients out of chronic psychiatric symptom sets  ...  For example, we discuss new treatments that target brain glutamate systems at key transition points within longitudinal courses of care that integrate several treatment modalities.  ...  NIDA was not involved in the content or preparation of this manuscript.  ... 
doi:10.20900/jpbs.20210008 pmid:34549091 pmcid:PMC8452258 fatcat:4sl3jnthcre3dgx5bdfozcjyuu

Application of Big Data Deep Learning in Auxiliary Diagnosis of Lower Extremity Arteriosclerosis Obliterans

Linbo Liu, Yang Liu, Hongjun Wang, Yi Zhang, Zhijie Liao, Shendong Du
2021 Journal of Clinical and Nursing Research  
Using big data deep learning technology to intelligently analyze a large number of image data, and then carry out auxiliary diagnosis, so as to improve the diagnosis and treatment effect of LEASO is the  ...  At this stage, China has entered the era of big data and artificial intelligence. Medical institutions at all levels can produce a large number of lower limb vascular image data every day.  ...  Convolutional neural network and support vector machine Convolution neural network is a representative algorithm of deep learning.  ... 
doi:10.26689/jcnr.v5i5.2573 fatcat:yu5p6oa2vnaprim76s3hojoljq

Artificial Intelligence in Lung Cancer Pathology Image Analysis

Shidan Wang, Donghan M. Yang, Ruichen Rong, Xiaowei Zhan, Junya Fujimoto, Hongyu Liu, John Minna, Ignacio Ivan Wistuba, Yang Xie, Guanghua Xiao
2019 Cancers  
With the rapid advance of medical imaging technology, whole slide imaging (WSI) in pathology is becoming a routine clinical procedure.  ...  lung cancer, and summarized the existing applications of deep learning algorithms in lung cancer diagnosis and prognosis.  ...  Inherent Characteristics and Advantages of Convolutional Neural Networks (CNNs) Inspired by the working mechanisms of the brain, deep neural networks, also called "deep learning", have one or more "hidden  ... 
doi:10.3390/cancers11111673 pmid:31661863 pmcid:PMC6895901 fatcat:bntqqbilwrbybdhgfd73px5zki

Deep anomaly detection for industrial systems: a case study

Feng Xue, Weizhong Yan, Tianyi Wang, Hao Huang, Bojun Feng
2020 Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM  
Both LSTM and CNN based deep neural network backbones are studied on the Secure Water Treatment (SWaT) testbed datasets.  ...  We formulate the problem as a self-supervised learning where data under normal operation is used to train a deep neural network autoregressive model, i.e., use a window of time series data to predict future  ...  ACKNOWLEDGMENT This material is based upon work supported by the Department of Energy, National Energy Technology Laboratory under Award Number DE-FE0031763.  ... 
doi:10.36001/phmconf.2020.v12i1.1186 fatcat:mtseixwucjebdjbnzli356c6rm

COVID-Net S: Towards computer-aided severity assessment via training and validation of deep neural networks for geographic extent and opacity extent scoring of chest X-rays for SARS-CoV-2 lung disease severity [article]

Alexander Wong, Zhong Qiu Lin, Linda Wang, Audrey G. Chung, Beiyi Shen, Almas Abbasi, Mahsa Hoshmand-Kochi, Timothy Q. Duong
2021 arXiv   pre-print
The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent  ...  A critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of the COVID-19 pandemic, is the assessment of the severity of disease  ...  Ethics approval The study has received ethics clearance from the University of Waterloo (42235).  ... 
arXiv:2005.12855v4 fatcat:redx5svoaneodpav4cnhzcnlfq
« Previous Showing results 1 — 15 out of 63,514 results