SS-SPS-3.3

Learning Properties of Feedforward Neural Networks Using Dual Numbers

Yuto Okawa, Tohru Nitta, Rikkyo University, Japan
Session:
Complex- and Hypercomplex-valued Adaptive Signal Processing
Track:
Signal Processing Systems: Design and Implementation (SPS)
Session Time:
Thu, 16 Dec, 16:20 - 18:20 Japan Standard Time (UTC +9)
Thu, 16 Dec, 07:20 - 09:20 Coordinated Universal Time
Thu, 16 Dec, 02:20 - 04:20 Eastern Standard Time (UTC -4)
Wed, 15 Dec, 23:20 - 01:20 Pacific Standard Time (UTC -7)
Session Co-Chairs:
Akira Hirose, The University of Tokyo and Isao Yamada, Tokyo Institute of Technology
Presentation
Not logged in.
Discussion
Not logged in.
Resources
Not logged in.
Session SS-SPS-3
TH3.LS-A.1: Generalization characteristics of complex-valued reservoir computing for interferometric synthetic aperture radar applications
Bungo Konishi, Akira Hirose, Ryo Natsuaki, The University of Tokyo, Japan
TH3.LS-A.2: A HYPERCOMPLEX TENSOR-SVD AND ITS APPLICATION
Takehiko Mizoguchi, NEC Laboratories America, Inc., United States of America; Isao Yamada, Tokyo Institute of Technology, Japan
TH3.LS-A.3: Learning Properties of Feedforward Neural Networks Using Dual Numbers
Yuto Okawa, Tohru Nitta, Rikkyo University, Japan
TH3.LS-A.4: ADAPTIVE SUBSURFACE IMAGING BASED ON PEAK PHASE-PROFILE: THE SIGNIFICANCE IN SEPARATION OF SCATTERING PHASE FROM PROPAGATION PHASE
Akira Hirose, Soshi Shimomura, The University of Tokyo, Japan
TH3.LS-A.5: DISCUSSION ON THE ORIGIN OF THE STRENGTH OF PHASOR QUATERNION SELF-ORGANIZING MAP
Yicheng Song, Akira Hirose, The University of Tokyo, Japan