Predicting the future with a scale-invariant temporal memory for the past
This addresses the challenge of efficient temporal prediction in complex systems, offering a novel approach for scenarios with multiple time scales, though it appears incremental in applying neural inspiration to existing prediction frameworks.
The paper tackles the problem of predicting future events by developing a neurally-inspired algorithm that uses a scale-invariant temporal memory of the past to generate scale-invariant predictions, and it demonstrates scalability on renewal processes where traditional methods face exponential state growth.
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.