Artificial intelligence (ai) and machine learning (ml)-based model switching techniques for neural network (nn)-based receivers

A system, comprising:

• at least one processor with a non-transitory computer-readable memory storing instructions executable by the at least one processor to:
• deploy a plurality of neural network receivers associated with a receiver component of a communications network, wherein the plurality of neural network receivers are trained to operate in different environments;
• receive sensing data associated with the receiver component;
• predict, based on the received sensing data, an environment for the receiver component from a predetermined set of different environment types;
• select a neural network receiver from the plurality of neural network receivers based on a probability of a successful decoding, wherein the selected neural network receiver is trained for the predicted environment;
• and
• switch to the selected neural network receiver to perform one or more operations of the receiver component.

A method to select a neural network receiver for a communications network, comprising:

• deploying a plurality of neural network receivers associated with a receiver component of the communications network, wherein the plurality of neural network receivers are trained to operate in different environments;
• predicting, based on received sensing data, an environment for the receiver component from a predetermined set of different environment types, wherein the received sensing data includes data associated with a signal received by the receiver component;
• and
• selecting the neural network receiver from the plurality of neural network receivers based on a probability of a successful decoding, wherein the selected neural network receiver is trained for the predicted environment.