scholarly journals A Survey on Silicon Photonics for Deep Learning

2021 ◽  
Vol 17 (4) ◽  
pp. 1-57
Author(s):  
Febin P. Sunny ◽  
Ebadollah Taheri ◽  
Mahdi Nikdast ◽  
Sudeep Pasricha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Language Processing ◽  
Integrated Circuit ◽  
Silicon Photonics ◽  
General Pattern ◽  
Network Models ◽  
Neural Network Models ◽  
Data Movement ◽  
Improved Performance

Deep learning has led to unprecedented successes in solving some very difficult problems in domains such as computer vision, natural language processing, and general pattern recognition. These achievements are the culmination of decades-long research into better training techniques and deeper neural network models, as well as improvements in hardware platforms that are used to train and execute the deep neural network models. Many application-specific integrated circuit (ASIC) hardware accelerators for deep learning have garnered interest in recent years due to their improved performance and energy-efficiency over conventional CPU and GPU architectures. However, these accelerators are constrained by fundamental bottlenecks due to (1) the slowdown in CMOS scaling, which has limited computational and performance-per-watt capabilities of emerging electronic processors; and (2) the use of metallic interconnects for data movement, which do not scale well and are a major cause of bandwidth, latency, and energy inefficiencies in almost every contemporary processor. Silicon photonics has emerged as a promising CMOS-compatible alternative to realize a new generation of deep learning accelerators that can use light for both communication and computation. This article surveys the landscape of silicon photonics to accelerate deep learning, with a coverage of developments across design abstractions in a bottom-up manner, to convey both the capabilities and limitations of the silicon photonics paradigm in the context of deep learning acceleration.

Feature extraction-based image steganalysis using deep learning

2021 ◽  
pp. 188-198
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Secure Communication ◽  
Information Technologies ◽  
Network Models ◽  
Error Rates ◽  
Multimedia Data ◽  
Secret Message ◽  
Neural Network Models

The innovations in advanced information technologies has led to rapid delivery and sharing of multimedia data like images and videos. The digital steganography offers ability to secure communication and imperative for internet. The image steganography is essential to preserve confidential information of security applications. The secret image is embedded within pixels. The embedding of secret message is done by applied with S-UNIWARD and WOW steganography. Hidden messages are reveled using steganalysis. The exploration of research interests focused on conventional fields and recent technological fields of steganalysis. This paper devises Convolutional neural network models for steganalysis. Convolutional neural network (CNN) is one of the most frequently used deep learning techniques. The Convolutional neural network is used to extract spatio-temporal information or features and classification. We have compared steganalysis outcome with AlexNet and SRNeT with same dataset. The stegnalytic error rates are compared with different payloads.

SEALing Neural Network Models in Encrypted Deep Learning Accelerators

2021 ◽  
Author(s):  
Pengfei Zuo ◽  
Yu Hua ◽  
Ling Liang ◽  
Xinfeng Xie ◽  
Xing Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Models ◽  
Neural Network Models

Beluga whale acoustic signal classification using deep learning neural network models

2020 ◽  
Vol 147 (3) ◽  
pp. 1834-1841 ◽  
Author(s):  
Ming Zhong ◽  
Manuel Castellote ◽  
Rahul Dodhia ◽  
Juan Lavista Ferres ◽  
Mandy Keogh ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Acoustic Signal ◽  
Network Models ◽  
Beluga Whale ◽  
Signal Classification ◽  
Neural Network Models ◽  
Deep Learning Neural Network

Application of Deep Learning for Characterization of Drivers’ Engagement in Secondary Tasks in In-Vehicle Systems

2020 ◽  
Vol 2674 (8) ◽  
pp. 429-440
Author(s):  
Osama A. Osman ◽  
Hesham Rakha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Time Series Data ◽  
Short Term Memory ◽  
Network Models ◽  
Sensor Technology ◽  
Series Data ◽  
Neural Network Models ◽  
Secondary Tasks ◽  
Driving Assistance

Distracted driving (i.e., engaging in secondary tasks) is an epidemic that threatens the lives of thousands every year. Data collected from vehicular sensor technologies and through connectivity provide comprehensive information that, if used to detect driver engagement in secondary tasks, could save thousands of lives and millions of dollars. This study investigates the possibility of achieving this goal using promising deep learning tools. Specifically, two deep neural network models (a multilayer perceptron neural network model and a long short-term memory networks [LSTMN] model) were developed to identify three secondary tasks: cellphone calling, cellphone texting, and conversation with adjacent passengers. The Second Strategic Highway Research Program Naturalistic Driving Study (SHRP 2 NDS) time series data, collected using vehicle sensor technology, were used to train and test the model. The results show excellent performance for the developed models, with a slight improvement for the LSTMN model, with overall classification accuracies ranging between 95 and 96%. Specifically, the models are able to identify the different types of secondary tasks with high accuracies of 100% for calling, 96%–97% for texting, 90%–91% for conversation, and 95%–96% for the normal driving. Based on this performance, the developed models improve on the results of a previous model developed by the author to classify the same three secondary tasks, which had an accuracy of 82%. The model is promising for use in in-vehicle driving assistance technology to report engagement in unlawful tasks or alert drivers to take over control in level 1 and 2 automated vehicles.

scholarly journals Comparison of rule-based and neural network models for negation detection in radiology reports

2020 ◽  
pp. 1-22 ◽  
Author(s):  
D. Sykes ◽  
A. Grivas ◽  
C. Grover ◽  
R. Tobin ◽  
C. Sudlow ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Language Processing ◽  
Network Models ◽  
Neural Network Models ◽  
Test Set ◽  
Rule Based ◽  
Radiology Reports ◽  
The Neural Network ◽  
Negation Detection

Abstract Using natural language processing, it is possible to extract structured information from raw text in the electronic health record (EHR) at reasonably high accuracy. However, the accurate distinction between negated and non-negated mentions of clinical terms remains a challenge. EHR text includes cases where diseases are stated not to be present or only hypothesised, meaning a disease can be mentioned in a report when it is not being reported as present. This makes tasks such as document classification and summarisation more difficult. We have developed the rule-based EdIE-R-Neg, part of an existing text mining pipeline called EdIE-R (Edinburgh Information Extraction for Radiology reports), developed to process brain imaging reports, (https://www.ltg.ed.ac.uk/software/edie-r/) and two machine learning approaches; one using a bidirectional long short-term memory network and another using a feedforward neural network. These were developed on data from the Edinburgh Stroke Study (ESS) and tested on data from routine reports from NHS Tayside (Tayside). Both datasets consist of written reports from medical scans. These models are compared with two existing rule-based models: pyConText (Harkema et al. 2009. Journal of Biomedical Informatics42(5), 839–851), a python implementation of a generalisation of NegEx, and NegBio (Peng et al. 2017. NegBio: A high-performance tool for negation and uncertainty detection in radiology reports. arXiv e-prints, p. arXiv:1712.05898), which identifies negation scopes through patterns applied to a syntactic representation of the sentence. On both the test set of the dataset from which our models were developed, as well as the largely similar Tayside test set, the neural network models and our custom-built rule-based system outperformed the existing methods. EdIE-R-Neg scored highest on F1 score, particularly on the test set of the Tayside dataset, from which no development data were used in these experiments, showing the power of custom-built rule-based systems for negation detection on datasets of this size. The performance gap of the machine learning models to EdIE-R-Neg on the Tayside test set was reduced through adding development Tayside data into the ESS training set, demonstrating the adaptability of the neural network models.

IMPROVED PERFORMANCE OF THE HOPFIELD AND LITTLE NEURAL NETWORK MODELS WITH TIME DELAYED DYNAMICS

1995 ◽  
Vol 09 (23) ◽  
pp. 3025-3037 ◽  
Author(s):  
PRABAL K MAITI ◽  
PRABIR K DASGUPTA ◽  
BIKAS K CHAKRABARTI
Keyword(s):  
Neural Network ◽  
Finite Size ◽  
Size Variation ◽  
Network Models ◽  
Internal Field ◽  
Neural Network Models ◽  
Delay Term ◽  
Previous Indication ◽  
Improved Performance ◽  
To Come

We report the results of simulation of neural network models with the synaptic connections constructed using the Hebb’s rule and the dynamics determined by the internal field, which has a weighted contribution from the time delayed signals. We consider both the asynchronous (or Glauber; Hopfield) and synchronous (Little) dynamics. Our numerical results and the finite size variation study (for sizes N within the range 250 ≤N≤4000) support the previous indication [Sen and Chakrabarti, Phys. Lett.A162, 327 (1992)] of improved performance in the recall and overlap properties in the thermodynamic limit. It is identified that the time delayed term in the dynamics allows the network to come out of the spurious valleys in the “energy landscape” (defined without the delay term; Hopfield model). In an approximate analytical study of such models in the extreme dilution limit, the role of the time delayed term to suppress the (spin glass-like) noise is also indicated.

scholarly journals Deep Learning-based Integrated Stacked Model for the Stock Market Prediction

2019 ◽  
Vol 9 (1) ◽  
pp. 5167-5174 ◽  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Learning ◽  
Stock Market ◽  
Network Models ◽  
Time Series Forecasting ◽  
Convolution Neural Network ◽  
Neural Network Models ◽  
Stock Market Prediction ◽  
Market Data

Recently, the stock market prediction has become one of the essential application areas of time-series forecasting research. The successful prediction of the stock market can be better guided to the investors to maximize their profit and to minimize the risk of investment. The stock market data are very much complex, non-linear and dynamic. Due to this reason, still, it is a challenging task. In recent time, deep learning method has become one of the most popular machine learning methods for time-series forecasting due to their temporal feature extraction capabilities. In this paper, we have proposed a novel Deep Learning-based Integrated Stacked Model (DISM) that integrates both the 1D Convolution neural network and LSTM recurrent neural network to find the spatial and temporal features from the stock market data. Our proposed DISM is applied to forecast the stock market. Here, we have also compared our proposed DISM with the single structured stacked LSTM, and 1D Convolution neural network models, and some other statistical models. We have observed that our proposed DISM produces better results in terms of accuracy and stability.

scholarly journals Predicting Success of Outbound Telemarketing in Insurance Policy Loans Using an Explainable Multiple-Filter Convolutional Neural Network

2021 ◽  
Vol 11 (15) ◽  
pp. 7147
Author(s):  
Jinmo Gu ◽  
Jinhyuk Na ◽  
Jeongeun Park ◽  
Hayoung Kim
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
False Positive Rate ◽  
Direct Marketing ◽  
Network Models ◽  
Learning Models ◽  
Insurance Policy ◽  
Neural Network Models ◽  
Potential Customers

Outbound telemarketing is an efficient direct marketing method wherein telemarketers solicit potential customers by phone to purchase or subscribe to products or services. However, those who are not interested in the information or offers provided by outbound telemarketing generally experience such interactions negatively because they perceive telemarketing as spam. In this study, therefore, we investigate the use of deep learning models to predict the success of outbound telemarketing for insurance policy loans. We propose an explainable multiple-filter convolutional neural network model called XmCNN that can alleviate overfitting and extract various high-level features using hundreds of input variables. To enable the practical application of the proposed method, we also examine ensemble models to further improve its performance. We experimentally demonstrate that the proposed XmCNN significantly outperformed conventional deep neural network models and machine learning models. Furthermore, a deep learning ensemble model constructed using the XmCNN architecture achieved the lowest false positive rate (4.92%) and the highest F1-score (87.47%). We identified important variables influencing insurance policy loan prediction through the proposed model, suggesting that these factors should be considered in practice. The proposed method may increase the efficiency of outbound telemarketing and reduce the spam problems caused by calling non-potential customers.

Sign in / Sign up

Export Citation Format

Share Document