یادگیری عمیق و نظریه تعادل نقطه ای
ترجمه نشده

یادگیری عمیق و نظریه تعادل نقطه ای

عنوان فارسی مقاله: یادگیری عمیق و نظریه تعادل نقطه ای
عنوان انگلیسی مقاله: Deep learning and punctuated equilibrium theory
مجله/کنفرانس: Cognitive Systems Research
رشته های تحصیلی مرتبط: مهندسی کامپیوتر
گرایش های تحصیلی مرتبط: هوش مصنوعی
کلمات کلیدی فارسی: یادگیری عمیق، شبکه های عصبی، تعادل نقطه ای، فرایند خط مشی، انتشار بازگشتی
کلمات کلیدی انگلیسی: Deep learning, Neural networks, Punctuated equilibrium, Policy process, Backpropagation
نوع نگارش مقاله: مقاله پژوهشی (Research Article)
نمایه: Scopus – Master Journals – JCR
شناسه دیجیتال (DOI): https://doi.org/10.1016/j.cogsys.2017.02.006
دانشگاه: Bavarian School of Public Policy, Technical University of Munich, Richard-Wagner-Str. 1, D-80333 Munich, Germany
ناشر: الزویر - Elsevier
نوع ارائه مقاله: ژورنال
نوع مقاله: ISI
سال انتشار مقاله: 2017
ایمپکت فاکتور: 1.450 در سال 2017
شاخص H_index: 41 در سال 2019
شاخص SJR: 0.303 در سال 2017
شناسه ISSN: 1389-0417
شاخص Quartile (چارک): Q4 در سال 2017
فرمت مقاله انگلیسی: PDF
تعداد صفحات مقاله انگلیسی: 11
وضعیت ترجمه: ترجمه نشده است
قیمت مقاله انگلیسی: رایگان
آیا این مقاله بیس است: خیر
کد محصول: E11783
فهرست انگلیسی مطالب

Abstract
1- Introduction
2- What is deep learning?
3- Policy process as information processing
4- A showcase model: deep learning and the policy process
5- Linking theories of budgetary politics to the politics of attention
6- Advanced deep learning
7- Outlook
Appendix A. Additional tables and data
References

نمونه متن انگلیسی مقاله

Abstract


Deep learning is associated with the latest success stories in AI. In particular, deep neural networks are applied in increasingly different fields to model complex processes. Interestingly, the underlying algorithm of backpropagation was originally designed for political science models. The theoretical foundations of this approach are very similar to the concept of Punctuated Equilibrium Theory (PET). The article discusses the concept of deep learning and shows parallels to PET. A showcase model demonstrates how deep learning can be used to provide a missing link in the study of the policy process: the connection between attention in the political system (as inputs) and budget shifts (as outputs).


Introduction


Deep learning is associated with the latest success stories in AI. From autonomous cars to AI beating a Go-master: deep learning is the method of choice to construct machine learning models that are useful in many complex situations. Taking this success-story into account, it seems obvious that political science could profit from this method as well. A whole branch of political science approaches sees the policy process as a kind of cognitive system that transforms political inputs from society into outputs. Punctuated Equilibrium Theory (PET) is a very successful concept in political science that is grounded in the theoretical works of Herbert Simon on bounded rationality (Simon, 1955). What separates this approach from rational choice theories is - amongst others - the understanding of organizations (Jones, 2003). While theories that rely solely on market mechanisms can see organizations only as individuals (maximizing their utility function) or as markets, where individuals meet. In bounded rationality organizations are seen as cooperations of individuals identifying with the organization. In many cases, this makes organizations much more effective than markets, especially because parallel processes can be organized with less information costs. But this makes organizations quite complex, as well.

  • اشتراک گذاری در

دیدگاه خود را بنویسید:

تاکنون دیدگاهی برای این نوشته ارسال نشده است

یادگیری عمیق و نظریه تعادل نقطه ای
نوشته های مرتبط
مقالات جدید
نماد اعتماد الکترونیکی
پیوندها