most citedNew Reinforcement Learning Using a Chaotic Neural Network for Emergence of "Thinking" - "Exploration" Grows into "Thinking" through Learning -

6 citations · 6 across the 1 of their papers we have counts for

collaborators

2 papers

cs.NE2020

Sensitivity - Local Index to Control Chaoticity or Gradient Globally -

Katsunari Shibata, Takuya Ejima, Yuki Tokumaru +1

Here, we introduce a fully local index named "sensitivity" for each neuron to control chaoticity or gradient globally in a neural network (NN). We also propose a learning method to…

cs.AI2017★ 6 cited

New Reinforcement Learning Using a Chaotic Neural Network for Emergence of "Thinking" - "Exploration" Grows into "Thinking" through Learning -

Katsunari Shibata, Yuki Goto

Expectation for the emergence of higher functions is getting larger in the framework of end-to-end reinforcement learning using a recurrent neural network. However, the emergence o…