| CPC G06N 3/047 (2023.01) [G06N 3/08 (2013.01)] | 20 Claims |
|
1. A system for a machine learning architecture for time series data prediction comprising:
a processor; and
a memory coupled to the processor and storing processor-executable instructions that, when executed, configure the processor to:
obtain time series data associated with a data query;
generate a predicted value by executing a machine learning application based on a sampled realization of the time series data, the machine learning application comprising a continuous time generative model trained to define an invertible mapping to maximize a log-likelihood of a set of predicted values for a time range associated with the time series data, wherein generation of the predicted value comprises:
computing the predicted value based on a joint distribution Xτ=Fθ(Wτ;τ), ∀τ∈[0, T], where Fθ(⋅; τ):
 d→d is the invertible mapping parametrized by the learnable parameters θ for every τ∈[0, T], and Wτ is a d-dimensional Wiener process, such that the log-likelihood is maximized, where pX(x) represents a probability density function of x;
wherein the invertible mapping is based on solving an initial value problem defined by:
 where hτ(t)∈
d, t∈[t0,t1], ƒθ:d××[t0,t1]→d, and gθ:×[to,t1]→, and the joint distribution Fθ(wτ; τ) is defined as a solution of hτ(t); andgenerate a signal providing an indication of the predicted value associated with the data query for performing a downstream task.
|