کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
404157 | 677393 | 2015 | 5 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Hodge–Kodaira decomposition of evolving neural networks
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
پیش نمایش صفحه اول مقاله
![عکس صفحه اول مقاله: Hodge–Kodaira decomposition of evolving neural networks Hodge–Kodaira decomposition of evolving neural networks](/preview/png/404157.png)
چکیده انگلیسی
Although it is very important to scrutinize recurrent structures of neural networks for elucidating brain functions, conventional methods often have difficulty in characterizing global loops within a network systematically. Here we applied the Hodge–Kodaira decomposition, a topological method, to an evolving neural network model in order to characterize its loop structure. By controlling a learning rule parametrically, we found that a model with an STDP-rule, which tends to form paths coincident with causal firing orders, had the most loops. Furthermore, by counting the number of global loops in the network, we detected the inhomogeneity inside the chaotic region, which is usually considered intractable.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neural Networks - Volume 62, February 2015, Pages 20–24
Journal: Neural Networks - Volume 62, February 2015, Pages 20–24
نویسندگان
Keiji Miura, Takaaki Aoki,