4.7 Article

A computational model of familiarity detection for natural pictures, abstract images, and random patterns: Combination of deep learning and anti-Hebbian training

期刊

NEURAL NETWORKS
卷 143, 期 -, 页码 628-637

出版社

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2021.07.022

关键词

Recognition memory; Familiarity recognition; Deep learning; Anti-Hebbian rule; Memorization

向作者/读者索取更多资源

The FaRe model utilizes a two-stage system for familiarity recognition of different types of images. It extracts image parameters in the first stage and makes decisions using a neural network in the second. The model demonstrates high capacity for familiarity recognition memory of natural pictures, but low capacity for abstract images and random patterns.
We present a neural network model for familiarity recognition of different types of images in the perirhinal cortex (the FaRe model). The model is designed as a two-stage system. At the first stage, the parameters of an image are extracted by a pretrained deep learning convolutional neural network. At the second stage, a two-layer feed forward neural network with anti-Hebbian learning is used to make the decision about the familiarity of the image. FaRe model simulations demonstrate high capacity of familiarity recognition memory for natural pictures and low capacity for both abstract images and random patterns. These findings are in agreement with psychological experiments. (C) 2021 Elsevier Ltd. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据