How the (Tensor-) Brain uses Embeddings and Embodiment to Encode Senses and Symbols

TL;DR

This paper presents the Tensor Brain model, a computational framework that integrates embeddings and embodiment to encode senses and symbols, bridging perception, memory, and symbolic reasoning.

Contribution

It introduces a novel two-layer Tensor Brain model combining subsymbolic and symbolic representations with concept embeddings for unified perception and memory.

Findings

The model effectively links sensory input to symbolic concepts.

Embeddings serve as a unified knowledge representation.

Top-down and bottom-up processes enable dynamic perception and reasoning.

Abstract

The Tensor Brain (TB) has been introduced as a computational model for perception and memory. This paper provides an overview of the TB model, incorporating recent developments and insights into its functionality. The TB is composed of two primary layers: the representation layer and the index layer. The representation layer serves as a model for the subsymbolic global workspace, a concept derived from consciousness research. Its state represents the cognitive brain state, capturing the dynamic interplay of sensory and cognitive processes. The index layer, in contrast, contains symbolic representations for concepts, time instances, and predicates. In a bottom-up operation, sensory input activates the representation layer, which then triggers associated symbolic labels in the index layer. Conversely, in a top-down operation, symbols in the index layer activate the representation layer, which in turn influences earlier processing layers through embodiment. This top-down mechanism underpins semantic memory, enabling the integration of abstract knowledge into perceptual and cognitive processes. A key feature of the TB is its use of concept embeddings, which function as connection weights linking the index layer to the representation layer. As a concept's ``DNA,'' these embeddings consolidate knowledge from diverse experiences, sensory modalities, and symbolic representations, providing a unified framework for learning and memory.