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

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.

Automated summary

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.