Predictive learning as a network mechanism for extracting low-dimensional latent space representations

Abstract

Neural networks have achieved many recent successes in solving sequential processing and planning tasks. Their success is often ascribed to the emergence of the task's low-dimensional latent structure in the network activity -i.e., in the learned neural representations. Similarly, biological neural circuits and in particular the hippocampus may produce representations that organize semantically related episodes. Here, we investigate the hypothesis that representations with low-dimensional latent structure, reflecting such semantic organization, result from learning to predict observations about the world. Specifically, we ask whether and when network mechanisms for sensory prediction coincide with those for extracting the underlying latent variables. Using a recurrent neural network model trained to predict a sequence of observations in a simulated spatial navigation task, we show that network dynamics exhibit low-dimensional but nonlinearly transformed representations of sensory inputs that capture the latent structure of the sensory environment. We quantify these results using nonlinear measures of intrinsic dimensionality which highlight the importance of the predictive aspect of neural representations, and provide mathematical arguments for when and why these representations emerge. We focus throughout on how our results can aid the analysis and interpretation of experimental data.

Self-healing codes: how stable neural populations can track continually reconfiguring neural representations

“…We first consider a network that uses inhibitory feedback to cancel the predictable aspects of its input. This is in line with models of predictive coding (58–60). We then consider a linear-nonlinear mapping that provides a prediction of y ( θ ) from a partially corrupted readout, using this signal to retrain readout weights.…”

The hippocampal formation as a hierarchical generative model supporting generative replay and continual learning

“…In other words, while sequences encode short-term predictions, maps encode long-term, average predictions of future locations. Our view is then compatible with the idea tat the hippocampus learns a predictive representation 75 but proposes that it is hierarchical.…”

Reach-dependent reorientation of rotational dynamics in motor cortex

“…Second, using different dimensions for different reach conditions can allow learning of multiple behaviors without catastrophic interference 47 , which is otherwise a major challenge for neural networks. Third, the use of distant portions of a curved manifold can reduce interference between conditions 48 , while reaping the benefit of strong generalization due to local linearity 49,50 . Finally, by allowing rotations to pivot in higher-dimensional space, the system can control each output dimension with much greater flexibility than if limited to planar rotational dynamics.…”