Experience-driven formation of parts-based representations in a model of layered visual memory

TL;DR

This paper presents a biologically inspired hierarchical model that self-organizes to form parts-based visual representations, enabling efficient, unsupervised face recognition through experience-driven learning mechanisms.

Contribution

It introduces a novel neural model combining synaptic plasticity and homeostatic regulation for forming parts-based memory traces in an unsupervised, incremental learning setting.

Findings

Model successfully forms local facial feature representations.

Higher layer captures individual identities explicitly.

Memory traces are sparse during recall and storage.

Abstract

Growing neuropsychological and neurophysiological evidence suggests that the visual cortex uses parts-based representations to encode, store and retrieve relevant objects. In such a scheme, objects are represented as a set of spatially distributed local features, or parts, arranged in stereotypical fashion. To encode the local appearance and to represent the relations between the constituent parts, there has to be an appropriate memory structure formed by previous experience with visual objects. Here, we propose a model how a hierarchical memory structure supporting efficient storage and rapid recall of parts-based representations can be established by an experience-driven process of self-organization. The process is based on the collaboration of slow bidirectional synaptic plasticity and homeostatic unit activity regulation, both running at the top of fast activity dynamics with winner-take-all character modulated by an oscillatory rhythm. These neural mechanisms lay down the basis for cooperation and competition between the distributed units and their synaptic connections. Choosing human face recognition as a test task, we show that, under the condition of open-ended, unsupervised incremental learning, the system is able to form memory traces for individual faces in a parts-based fashion. On a lower memory layer the synaptic structure is developed to represent local facial features and their interrelations, while the identities of different persons are captured explicitly on a higher layer. An additional property of the resulting representations is the sparseness of both the activity during the recall and the synaptic patterns comprising the memory traces.