How is space-time represented in the brain? : The math behind a predictive fuzzy memory network

Abstract: Neural Networks perform parallel computations in a fuzzy (meaning imprecise) fashion to represent space, time and memory, which in turn can be flexibly used for decision-making with regard to potential future events. A basic question to be addressed is— How will the mathematical representation of the past (memory) determine the ability to predict the future?  I will present a neural-net model where the connection weights are derived as an inverse-Laplace transform operation, and is uniquely suited for flexibly time-translating memory states by modulating  those connections. I will try to convince you that the computational simplicity of this neural-network architecture provides all the flexibility needed to store and extract space, time and memory representations. Over and beyond showing neuroscientific evidence for a fuzzy memory network, I will demonstrate that Predictive algorithms in machine learning can significantly benefit from incorporating such a fuzzy memory network in improving their predictive power.