Robust Spike-Based Continual Meta-Learning Improved by Restricted Minimum Error Entropy Criterion
Round 1
Reviewer 1 Report
The propose of paper a novel spike-based framework with minimum error entropy, called MeMEE, using the entropy theory to establish the gradient-based online meta-learning scheme in a recurrent SNN architecture.
I think that this study provides new perspectives for further integration of advanced information theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems.
First of all the introduction of paper provide sufficient background and include all relevant references. Also, the research is designed and described appropriately in content presented.
the results of study clearly presented as below.
This study first presented a information theoretical learning based scheme for robust spike-based continual meta-learning, which is improved by the RMEE criterion.
Author Response
We appreciate all your positive comments on the significance of our contributions and the scientific value of our research. At the same time, we have improved the language of this paper and some description in this paper.
Reviewer 2 Report
This is a novel research paper with original contributions in the area of Spiking Neural Networks.
Author Response
We appreciate all your positive comments on the significance of our contributions and the scientific value of our research. At the same time, we have improved the language of this paper and some description in this paper.
