Ryo Karakida

According to our database1, Ryo Karakida authored at least 24 papers between 2016 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Self-attention Networks Localize When QK-eigenspectrum Concentrates.
CoRR, 2024

2023
Attention in a Family of Boltzmann Machines Emerging From Modern Hopfield Networks.
Neural Comput., August, 2023

Deep learning in random neural fields: Numerical experiments via neural tangent kernel.
Neural Networks, March, 2023

On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width.
CoRR, 2023

MLP-Mixer as a Wide and Sparse MLP.
CoRR, 2023

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias.
Proceedings of the International Conference on Machine Learning, 2023

2022
Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks.
Neural Comput., 2021

Self-paced data augmentation for training neural networks.
Neurocomputing, 2021

Learning Curves for Sequential Training of Neural Networks: Self-Knowledge Transfer and Forgetting.
CoRR, 2021

The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019
Information Geometry for Regularized Optimal Transport and Barycenters of Patterns.
Neural Comput., 2019

The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Fisher Information and Natural Gradient Learning in Random Deep Networks.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited.
Neural Comput., 2018

Statistical Neurodynamics of Deep Networks: Geometry of Signal Spaces.
CoRR, 2018

2017
Concept Formation and Dynamics of Repeated Inference in Deep Generative Models.
CoRR, 2017

Information Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem.
CoRR, 2017

Information Geometry of Wasserstein Divergence.
Proceedings of the Geometric Science of Information - Third International Conference, 2017

2016
Dynamical analysis of contrastive divergence learning: Restricted Boltzmann machines with Gaussian visible units.
Neural Networks, 2016

Adaptive Natural Gradient Learning Algorithms for Unnormalized Statistical Models.
Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2016, 2016

Maximum likelihood learning of RBMs with Gaussian visible units on the Stiefel manifold.
Proceedings of the 24th European Symposium on Artificial Neural Networks, 2016


  Loading...