2021/01/26 by Wei Zhong Goh, Goh, Wei Zhong, Varun Ursekar +3
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Neural Networks and Applications #Neural dynamics and brain function #Neurons and Cognition (q-bio.NC)
paper · pdf · doi:10.48550/arxiv.2101.10953
openalex publication_date 2021/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In recent years it has become clear that the brain maintains a temporal\nmemory of recent events stretching far into the past. This paper presents a\nneurally-inspired algorithm to use a scale-invariant temporal representation of\nthe past to predict a scale-invariant future. The result is a scale-invariant\nestimate of future events as a function of the time at which they are expected\nto occur. The algorithm is time-local, with credit assigned to the present\nevent by observing how it affects the prediction of the future. To illustrate\nthe potential utility of this approach, we test the model on simultaneous\nrenewal processes with different time scales. The algorithm scales well on\nthese problems despite the fact that the number of states needed to describe\nthem as a Markov process grows exponentially.\n