کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
4969444 1449935 2016 23 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Understanding convolutional neural networks with a mathematical model
ترجمه فارسی عنوان
درک شبکه های عصبی کانولوشن با یک مدل ریاضی
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): (1) why a nonlinear activation function is essential at the filter output of all intermediate layers? (2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the “REctified-COrrelations on a Sphere” (RECOS) is proposed to answer these two questions. After the CNN training process, the converged filter weights define a set of anchor vectors in the RECOS model. Anchor vectors represent the frequently occurring patterns (or the spectral components). The necessity of rectification is explained using the RECOS model. Then, the behavior of a two-layer RECOS system is analyzed and compared with its one-layer counterpart. The LeNet-5 and the MNIST dataset are used to illustrate discussion points. Finally, the RECOS model is generalized to a multilayer system with the AlexNet as an example.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Visual Communication and Image Representation - Volume 41, November 2016, Pages 406-413
نویسندگان
,