آموزش شبکه عصبی
ترجمه نشده

آموزش شبکه عصبی

عنوان فارسی مقاله: یادگیری وزنی دشوار: یک رویکرد جدید مانند برنامه درسی مبتنی بر مثالهای دشوار برای آموزش شبکه عصبی
عنوان انگلیسی مقاله: Difficulty-Weighted Learning: A Novel Curriculum-Like Approach Based on Difficult Examples for Neural Network Training
مجله/کنفرانس: سیستم های خبره با کابردهای مربوطه – Expert Systems with Applications
رشته های تحصیلی مرتبط: مهندسی کامپیوتر، مهندسی فناوری اطلاعات
گرایش های تحصیلی مرتبط: هوش مصنوعی، شبکه های کامپیوتری
کلمات کلیدی فارسی: شبکه عصبی، یادگیری برنامه درسی، یادگیری نظارتی، یادگیری عمیق، ادراک چند لایه، طبقه بندی
کلمات کلیدی انگلیسی: Neural network; Curriculum learning; Supervised learning; Deep learning; Multilayer perceptron; Classification
نوع نگارش مقاله: مقاله پژوهشی (Research Article)
نمایه: Scopus – Master Journals List – JCR
شناسه دیجیتال (DOI): https://doi.org/10.1016/j.eswa.2019.06.017
دانشگاه: Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, 2-4-7 Aomi, Koto-ku, Tokyo, Japan
ناشر: الزویر - Elsevier
نوع ارائه مقاله: ژورنال
نوع مقاله: ISI
سال انتشار مقاله: 2019
ایمپکت فاکتور: 5.891 در سال 2018
شاخص H_index: 162 در سال 2019
شاخص SJR: 1.190 در سال 2018
شناسه ISSN: 0957-4174
شاخص Quartile (چارک): Q1 در سال 2018
فرمت مقاله انگلیسی: PDF
تعداد صفحات مقاله انگلیسی: 18
وضعیت ترجمه: ترجمه نشده است
قیمت مقاله انگلیسی: رایگان
آیا این مقاله بیس است: خیر
آیا این مقاله مدل مفهومی دارد: ندارد
آیا این مقاله پرسشنامه دارد: ندارد
آیا این مقاله متغیر دارد: ندارد
کد محصول: E13555
رفرنس: دارای رفرنس در داخل متن و انتهای مقاله
فهرست انگلیسی مطالب

Abstract


1. Introduction


2. Related work


3. Difficulty-weighted learning


4. Evaluation


5. Results and discussion


6. Summary and future work


CRediT authorship contribution statement


Conflict of interest


Acknowledgement


References

نمونه متن انگلیسی مقاله

Abstract


Curriculum learning, in which training examples gradually proceed from easy to difficulty, has been applied to various tasks and demonstrated better performance than other machine learning approaches. However, identifying the difficulty level in advance often requires domain knowledge and is a time-consuming process. We dynamically decide the difficulty of examples based on outputs from neural networks during training and propose a loss function to promote training with difficult examples. Experimental results verify that the proposed method improves the generalization ability across several datasets.


Introduction


Neural networks have been demonstrating excellent classification performance for various datasets of images, audio, language, among others. This performance has relied on the development of robust training methods such as fine-tuning (Hinton and Salakhutdinov, 2006; Mesnil et al., 2012; Yosinski et al., 2014) and generative adversarial networks (Goodfellow et al., 2014; Radford, Metz, and Chintala, 2015). Curriculum learning, proposed by Bengio et al. (2009), is another powerful training method, in which learning gradually proceeds from easy to difficult examples, aiming to resemble human learning. Its proponents successfully applied curriculum learning to classification of geometric shapes and language processing. In this paper, we prioritize the classification of difficult examples over easy examples. Therefore, we focus on the training of difficult examples and employ the conventional curriculum learning (Bengio et al., 2009) to train easy examples. A training strategy based on difficulty can be easily implemented in neural networks, because the classification outputs represent the degree of confidence, that is, the difficulty of the examples. To increase the weight of difficult examples over easy ones, we use a loss function weighted by the network outputs. As the loss function is determined at each iteration, it can reflect the varying difficulty of examples, establishing the proposed method, which we call difficulty-weighted learning (DWL). DWL is strongly related to expert systems because it automatically retrieves the difficulty level of examples based on the devised loss function, whereas conventional methods, such as curriculum learning (Bengio et al., 2009), require domain knowledge for each task. Furthermore, as DWL is supported by neural networks, which are powerful intelligent systems, the DWL implementation can be regarded as an expert and intelligent system.

  • اشتراک گذاری در

دیدگاه خود را بنویسید:

تاکنون دیدگاهی برای این نوشته ارسال نشده است

آموزش شبکه عصبی
نوشته های مرتبط
مقالات جدید
نماد اعتماد الکترونیکی
پیوندها