1.7k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Kyoto UniversityJP15 papers
- RIKEN Center for Advanced Intelligence ProjectJP6 papers
- National Institute of Information and Communications TechnologyJP4 papers
- Okinawa Institute of Science and Technology Graduate UniversityJP4 papers
- RIKENJP4 papers
- The University of TokyoJP4 papers
- Hitachi (Japan)JP3 papers
- Niigata UniversityJP3 papers
- University College LondonGB3 papers
- Xi'an Jiaotong UniversityCN3 papers
- Gatsby Computational Neuroscience UnitGB2 papers
- Kyoto College of Graduate Studies for InformaticsJP2 papers
8 papers · 1 filter
Correntropy-Based Improper Likelihood Model for Robust Electrophysiological Source Imaging
Yuanhao Li, Badong Chen, Zhongxu Hu +4
Bayesian learning provides a unified skeleton to solve the electrophysiological source imaging task. From this perspective, existing source imaging algorithms utilize the Gaussian…
Adaptive sparseness for correntropy-based robust regression via automatic relevance determination
Yuanhao Li, Badong Chen, Okito Yamashita +2
Sparseness and robustness are two important properties for many machine learning scenarios. In the present study, regarding the maximum correntropy criterion (MCC) based robust reg…
Model-Based Imitation Learning Using Entropy Regularization of Model and Policy
Eiji Uchibe
Approaches based on generative adversarial networks for imitation learning are promising because they are sample efficient in terms of expert demonstrations. However, training a ge…
Forward and inverse reinforcement learning sharing network weights and hyperparameters
Eiji Uchibe, Kenji Doya
This paper proposes model-free imitation learning named Entropy-Regularized Imitation Learning (ERIL) that minimizes the reverse Kullback-Leibler (KL) divergence. ERIL combines for…
Group-based Learning of Disentangled Representations with Generalizability for Novel Contents
Haruo Hosoya
Sensory data are often comprised of independent content and transformation factors. For example, face images may have shapes as content and poses as transformation. To infer separa…
One pixel attack for fooling deep neural networks
Jiawei Su, Danilo Vasconcellos Vargas, Sakurai Kouichi
Recent research has revealed that the output of Deep Neural Networks (DNN) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we ana…
Online Meta-learning by Parallel Algorithm Competition
Stefan Elfwing, Eiji Uchibe, Kenji Doya
The efficiency of reinforcement learning algorithms depends critically on a few meta-parameters that modulates the learning updates and the trade-off between exploration and exploi…
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
Stefan Elfwing, Eiji Uchibe, Kenji Doya
In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human…