AMI: An Auditory Machine Intelligence Algorithm for Predicting Sensory-Like Data

Authors : Emmanuel Ndidi Osegi, Vincent Anireh

Pages : 71-89

View : 13 | Download : 8

Publication Date : 2020-12-01

Article Type : Research

Abstract :In this paper, we present the results of our experiments using a new biologically constrained machine intelligence algorithm based on neural processing in the auditory cortex called auditory machine intelligence (AMI). This algorithm is an online learning technique for predicting sensory time series data i.e. data that comes in streams or a sequential order. The AMI algorithm is particularly inspired by the mismatch negativity effect which provides important evidence that the brain learns a statistical structure of the world it senses. We show through a number of experiments with popular benchmarks, how this algorithm may be applied in a real world sense. The results of these experiments have also been compared with two very popular techniques that have been used for time series predictions and are very encouraging.
Keywords : Auditory processing, biological machine intelligence, predictions, sensory data, time series