Picture for Isao Ishikawa

Isao Ishikawa

Constructive Universal Approximation Theorems for Deep Joint-Equivariant Networks by Schur's Lemma

Add code
May 22, 2024
Viaarxiv icon

Finite-dimensional approximations of push-forwards on locally analytic functionals and truncation of least-squares polynomials

Add code
Apr 16, 2024
Viaarxiv icon

Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces

Add code
Mar 14, 2024
Viaarxiv icon

A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks

Add code
Feb 25, 2024
Viaarxiv icon

Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks

Add code
Oct 05, 2023
Viaarxiv icon

Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks

Add code
Oct 05, 2023
Viaarxiv icon

Koopman-Based Bound for Generalization: New Aspect of Neural Networks Regarding Nonlinear Noise Filtering

Add code
Feb 12, 2023
Viaarxiv icon

Dynamic Structure Estimation from Bandit Feedback

Add code
Jun 02, 2022
Figure 1 for Dynamic Structure Estimation from Bandit Feedback
Figure 2 for Dynamic Structure Estimation from Bandit Feedback
Figure 3 for Dynamic Structure Estimation from Bandit Feedback
Figure 4 for Dynamic Structure Estimation from Bandit Feedback
Viaarxiv icon

Universality of group convolutional neural networks based on ridgelet analysis on groups

Add code
May 30, 2022
Viaarxiv icon

Universal approximation property of invertible neural networks

Add code
Apr 15, 2022
Figure 1 for Universal approximation property of invertible neural networks
Figure 2 for Universal approximation property of invertible neural networks
Figure 3 for Universal approximation property of invertible neural networks
Viaarxiv icon