Remembrance of things perceived: Adding thalamocortical function to artificial neural networks

Abstract

Recent research has illuminated the complexity and importance of the thalamocortical system but it has been difficult to identify what computational functions it performs. Meanwhile, deep-learning artificial neural networks (ANNs) based on bio-inspired models of purely cortical circuits have achieved surprising success solving sophisticated cognitive problems associated historically with human intelligence. Nevertheless, the limitations and shortcomings of artificial intelligence (AI) based on such ANNs are becoming increasingly clear. This review considers how the addition of thalamocortical connectivity and its putative functions related to cortical attention might address some of those shortcomings. Such bio-inspired models are now providing both testable theories of biological cognition and improved AI technology, much of which is happening outside the usual academic venues.

Keywords: attention; illusion; learning; memory; saliency; thalamus.

Figure 1

Corticothalamic recurrent circuits support similar computational functions in all cortical areas. The transmission of sensory information from all receptor modalities (except olfactory) to cortex is modulated in thalamus (valve symbol) and the excitability of the multiple primary sensory (S) cortical areas to that information is modulated by Narrow thalamocortical projections (!). If the sensory information is incongruent with any of the familiar expectations, corticothalamic activity leads to activation of Broad thalamocortical projections from non-sensory thalamic neurons that recruit cognitive processing by other sensory, associative (A) and motor (M) cortical areas, often culminating in the identification of an exploratory action to obtain additional sensory information about the unknown object. The thresholds for these thalamic recruitments of cortical functions (including overt exploratory actions) are set by the Basal Ganglia in consideration of a risk-benefit analysis. The Broad thalamocortical projections are also capable of Hebbian potentiation of their synapses onto currently active cortical neurons, providing a snapshot memory (camera icon) of the incongruent sensorimotor activity that can be replayed off-line by spontaneous activity in those thalamocortical neurons. The general locations of cortical inputs and outputs are shown by layers. The corticothalamic system adds sophisticated cognitive decision-making to a subcortical system (tectum, reticulospinal system, and cerebellum) that is itself capable of fast and accurate sensorimotor performance. Collateral discharge from this system passes through thalamic nuclei to motor cortical areas.

Figure 2

Recursive Cortical Network (RCN) model of primary visual cortex reproduced from George et al. (2020); with permission of the authors. (A) Model of microcolumn architecture with separate computational elements for feedforward and feedbackward computations associated with cortical layers 1–4 and 5–6 + thalamus, respectively. It uses factor graph notation for message passing between nodes (circles) via distributed, weighted projections (squares) that are integrated at nodes according to summative or multiplicative functions that can be realized neuromorphically. Messages pass in both directions along lines illustrated according to recursive connections among neurons within the microcolumn. The messages represent belief propagation based on the probability that a given feature is present in the pixel data from the retina. (B) Neuroanatomical representation of a model of visual cortex with columns for color detecting “blobs” and contour feature detecting “interblobs.” Lateral connections among Feature detectors allow Pool neurons to generalize contour feature detection across retinal locations. Intracortical feedback circuits generate illusory contours and their filling with adjacent color features. Narrow-type corticothalamocortical feedback results in Explaining Away, whereby partially occluded images are readily perceived because the occluding object provides an explanation for the missing contours. Broad-type corticothalamocortical projections generate Gated feedforward projections to other cortical areas. See George et al. (2020) for mathematical description of the various message passing functions and simulations of these visual perceptual phenomena.