WNN : File Format for Neural Network Interchange
รหัสดีโอไอ
Creator Anirudh Giri
Title WNN : File Format for Neural Network Interchange
Contributor -
Publisher Faculty of Science and Technology, Suan Sunandha Rajabhat University
Publication Year 2564
Journal Title Suan Sunandha Science and Technology Journal
Journal Vol. 8
Journal No. 1
Page no. 9 to 12
Keyword Artificial neural networks, File format, Neural network model sharing, Neural network modelsaving
URL Website www.ssstj.sci.ssru.ac.th
Website title Suan Sunandha Science and Technology Journal (SSSTJ)
ISSN 2351-0889
Abstract A programming language agnostic, neural network library agnostic, standardized file format used to save analready trained neural network model would facilitate the process of sharing or releasing said neural networkmodel online in a simplistic fashion. A standard file format for saving neural network models would includemetadata about the neural network such as the number of inputs, hidden layers, nodes per hidden layer, outputsand the activation function used along with the weights and bias values. Such a file can be parsed to reconstructa neural network model in any programming language or library and would remove a neural network model'sdependency on the library it was created on.
Suan Sunandha Science and Technology Journal

บรรณานุกรม

EndNote

APA

Chicago

MLA

ดิจิตอลไฟล์

Digital File
DOI Smart-Search
สวัสดีค่ะ ยินดีให้บริการสอบถาม และสืบค้นข้อมูลตัวระบุวัตถุดิจิทัล (ดีโอไอ) สำนักการวิจัยแห่งชาติ (วช.) ค่ะ