دانلود و نمایش مقالات مرتبط با Back propagation algorithm::صفحه 1
دانلود بهترین مقالات isi همراه با ترجمه فارسی 2

با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد). 

نتیجه جستجو - Back propagation algorithm

تعداد مقالات یافته شده: 6
ردیف عنوان نوع
1 Log-sum enhanced sparse deep neural network
شبکه عصبی پراکنده عمیق با افزایش log-sum-2020
How to design deep neural networks (DNNs) for the representation and analysis of high dimensional but small sample size data is still a big challenge. One solution is to construct a sparse network. At present, there exist many approaches to achieve sparsity for DNNs by regularization, but most of them are carried out only in the pre-training process due to the difficulty in the derivation of explicit formulae in the finetuning process. In this paper, a log-sum function is used as the regularization terms for both the responses of hidden neurons and the network connections in the loss function of the fine-tuning process. It provides a better approximation to the L0-norm than several often used norms. Based on the gradient formula of the loss function, the fine-tuning process can be executed more efficiently. Specifically, the commonly used gradient calculation in many deep learning research platforms, such as PyTorch or TensorFlow, can be accelerated. Given the analytic formula for calculating gradients used in any layer of DNN, the error accumulated from successive numerical approximations in the differentiation process can be avoided. With the proposed log-sum enhanced sparse deep neural network (LSES-DNN), the sparsity of the responses and the connections can be well controlled to improve the adaptivity of DNNs. The proposed model is applied to MRI data for both the diagnosis of schizophrenia and the study of brain developments. Numerical experiments demonstrate its superior performance among several classical classifiers tested.
Keywords: Deep neural network | Log-sum enhanced sparsity | Back propagation algorithm | Concise gradient formula | Magnetic resonance imaging
مقاله انگلیسی
2 Differential convolutional neural network
شبکه های عصبی تکاملی دیفرانسیلی-2019
Convolutional neural networks with strong representation ability of deep structures have ever increasing popularity in many research areas. The main difference of Convolutional Neural Networks with respect to existing similar artificial neural networks is the inclusion of the convolutional part. This inclusion directly increases the performance of artificial neural networks. This fact has led to the development of many different convolutional models and techniques. In this work, a novel convolution technique named as Differential Convolution and updated error back-propagation algorithm is proposed. The proposed technique aims to transfer feature maps containing directional activation differences to the next layer. This implementation takes the idea of how convolved features change on the feature map into consideration. In a sense, this process adapts the mathematical differentiation operation into the convolutional process. Proposed improved back propagation algorithm also considers neighborhood activation errors. This property increases the classification performance without changing the number of filters. Four different experiment sets were performed to observe the performance and the adaptability of the differential convolution technique. In the first experiment set utilization of the differential convolution on a traditional convolutional neural network structure made a performance boost up to 55.29% for the test accuracy. In the second experiment set differential convolution adaptation raised the top1 and top5 test accuracies of AlexNet by 5.3% and 4.75% on ImageNet dataset. In the third experiment set differential convolution utilized model outperformed all compared convolutional structures. In the fourth experiment set, the Differential VGGNet model obtained by adapting proposed differential convolution technique performed 93.58% and 75.06% accuracy values for CIFAR10 and CIFAR100 datasets, respectively. The accuracy values of the Differential NIN model containing differential convolution operation were 92.44% and 72.65% for the same datasets. In these experiment sets, it was observed that the differential convolution technique outperformed both traditional convolution and other compared convolution techniques. In addition, easy adaptation of the proposed technique to different convolutional structures and its efficiency demonstrate that popular deep learning models may be improved with differential convolution
Keywords: Convolutional neural networks | Deep learning | Image classification | Convolution techniques | Pattern recognition | Machine learning
مقاله انگلیسی
3 A hybrid SEM-neural network analysis of social media addiction
تجزیه و تحلیل شبکه عصبی SEM ترکیبی اعتیاد به رسانه های اجتماعی-2019
Social media has been a phenomenon but it is a double-edge sword that can bring about negative ef- fects such as social media addiction. Nevertheless, very less attention has been given in unveiling the determinants of social media addiction. In this study, artificial intelligence and expert systems were ap- plied through a hybrid SEM-artificial neural network approach to predict social media addiction. An inte- grated model of the Big Five Model and Uses and Gratification Theory was validated based on a sample of 615 Facebook users. Unlike existing social media studies that used SEM, in this study, we engaged a hybrid SEM-ANN approach with IPMA as the additional analysis. The new SEM-IPMA-ANN analysis is a novel methodological contribution where useful conclusion can be drawn based on not only the con- struct’s importance but also its performance in prioritizing managerial actions. Primary focus will be given in improving the performance of constructs that exhibit huge importance with relatively low per- formance. Based on the normalized importance of the ANN analysis using multilayer perceptrons with feed-forward-back propagation algorithm, we found nonlinear relationships between neuroticism and so- cial media addiction. This is a significant finding as previously only linear relationships were found. In addition, entertainment is the strongest predictor followed by agreeableness, neuroticism, hours spent and gender. The artificial neural network is able to predict social media addiction with an 86.67% accu- racy. The new methodology and findings from the study will give huge impacts to the extant literature of expert systems and artificial intelligence generally and social media addiction specifically. We discussed the methodological, theoretical and practical contributions of the study.
Keywords: Artificial intelligence | Neural network | Social media addiction | Big five model | Uses and gratifications theory | Personality trait
مقاله انگلیسی
4 Heterogeneous visual features integration for image recognition optimization in internet of things
یکپارچه سازی ویژگی های یکپارچه برای بهینه سازی تصویر در اینترنت از اشیا-2016
Recently, a large number of physical devices, together with distributed information systems, deployed in internet of things (IoT), are collecting more and more images. Such collected images recognition poses an important challenge on optimization in internet of things. Specially, most of existing methods only adopt shallow learning models to integrate various features of images for recognition limiting classification accuracy. In this paper, we propose a multimodal deep learning (MMDL) approach to integrate hetero geneous visual features by considering each type of visual feature as one modality for image recognition optimization in internet of things. In our scheme, we extract the high-level abstraction of each modality by a stacked autoencoders. Furthermore, we design a back propagation algorithm with shared weights learned from a softmax layer to update the pretrained parameters of multiple stacked autoencoders simultaneously. The integration is performed by concatenating the last hidden layers of the multimodal stacked autoencoders architecture. Extensive experiments are carried out on three datasets i.e. Ani mal with Attributes, NUS-WIDE-OBJECT, and Handwritten Numerals, by comparison with SVM, SAE, and AMMSS. Results demonstrate that our scheme has superior performance on heterogeneous visual features integration for image recognition optimization in internet of things.
Keywords: Multimodal integration optimization | Deep learning | Internet of things | Image classification | Stacked autoencoders
مقاله انگلیسی
5 بررسی عملکرد شبکه عصبی دارای تغذیه رو به جلو برای حریم هم ارز با وسایل باسیم/ پروتکل های دسترسی محافظت شده با وای فای
سال انتشار: 2016 - تعداد صفحات فایل pdf انگلیسی: 14 - تعداد صفحات فایل doc فارسی: 21
هدف: میلیون ها نفر بدون اینکه جنبه های فناوری بی سیم را بدانند، از وسایل بی سیم در زندگی کارهای روزانه خود استفاده می کنند. هدف تحقیق ما ارتقای اجرای پروتکل های وسایل بی سیم ازطریق بررسی رفتار آنها در شبکه عصبی دارای تغذیه رو به جلو می باشد که به صورت گسترده استفاده می شوند. اساسا" شبکه عصبی یک شبکه رشته ای چند لایه ای می باشد. این شبکه، داده های ثبت شده را یکی یکی پردازش می کند و ازطریق مقایسه خروجی به دست آمده با خروجی واقعی، به اطلاعات دست می یابد. رشته های عصبی دارای لایه پنهان یک نقش اصلی در عملکرد نشر و انتشار رو به عقب دارد. فرآیند تعیین تعداد رشته های عصبی دارای لایه پنهان هنوزهم مبهم است. این کار تحقیقی روی ارزیابی عملکرد رشته های عصبی دارای لایه پنهان برای پروتکل های WEP (حریم هم ارز با وسایل با سیم) و WPA (دسترسی محافظت شده با وای فای) متمرکز می باشد.
روشها/ تحلیل آماری: برای این کار، سه معماری شبکه ای جهت انجام تحلیل، انتخاب شده است. این کار تحقیقی با استفاده از الگوریتم انتشار رو به عقب در جعبه ابزار شبکه عصبی روی داده های به دست آمده با استفاده از ابزار وایرشارک، انجام می شود.
یافته ها: رفتار شبکه های عصبی غیر پنهان ازطریق روش شبیه سازی بررسی می شود. عملکرد شبکه نیز با کمک داده های تاریخی و خطای مربع میانگین (MSE) تشخیص داده می شود. عملکرد شبکه عصبی بررسی می شود و نتایج نشان می دهند که شبکه های عصبی دارای لایه پنهان بر کارکرد شبکه اثر می گذارند.
بهبود: ما دوست داریم که با پارامتر و یادگیری شبکه عصبی کار کنیم تا به بهترین نتایج دست یابیم.
کلیدواژه ها: انتشار رو به عقب | شبکه عصبی دارای تغذیه رو به جلو | لایه پنهان | خطای مربع میانگین | دسترسی محافظت شده با وای فای | حریم هم ارز با وسایل با سیم
مقاله ترجمه شده
6 Relevance Study of Data Mining for the Identification of Negatively Influenced Factors in Sick Groups
مطالعه ارتباط داده کاوی برای شناسایی عوامل منفی تحت تاثیر در گروه بیمار-2015
The application of medical data mining is emphasis with temporal data in this piece of writing. The application of computational methods in medical field is well known and which started in previous decades, but still now also lot of researches take place in artificial intelligence, knowledge discovery and mining. Correlating computational intelligence with medical intelligence to predict negatively influenced epidemiological factors in liver disorder patients.© 2015 The Authors. Published by Elsevier B.V.Peer-review under responsibility of organizing committee of the Graph Algorithms, High Performance Implementations and Applications (ICGHIA2014).© 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).Peer-review under responsibility of organizing committee of the Graph Algorithms, High Performance Implementations and Applications (ICGHIA2014)
Neural Networks | Back Propagation Algorithm | Analysis of Variance
مقاله انگلیسی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی
logo-samandehi
بازدید امروز: 2480 :::::::: بازدید دیروز: 0 :::::::: بازدید کل: 2480 :::::::: افراد آنلاین: 67