Predicting the future with a scale-invariant temporal memory for the past

TL;DR

This paper introduces a neurally-inspired, scale-invariant temporal memory algorithm that predicts future events across multiple time scales, mimicking brain-like memory and prediction capabilities.

Contribution

It presents a novel, time-local algorithm for scale-invariant temporal prediction, capable of handling multiple time scales efficiently.

Findings

Algorithm scales well with multiple time scales

Handles exponential growth in states efficiently

Demonstrates utility on renewal processes

Abstract

In recent years it has become clear that the brain maintains a temporal memory of recent events stretching far into the past. This paper presents a neurally-inspired algorithm to use a scale-invariant temporal representation of the past to predict a scale-invariant future. The result is a scale-invariant estimate of future events as a function of the time at which they are expected to occur. The algorithm is time-local, with credit assigned to the present event by observing how it affects the prediction of the future. To illustrate the potential utility of this approach, we test the model on simultaneous renewal processes with different time scales. The algorithm scales well on these problems despite the fact that the number of states needed to describe them as a Markov process grows exponentially.