Abstract: Provided are systems and methods for adaptive payload extraction and retransmission in wireless data communications. An example method commences with transmitting a network packet to a receiver via a communication channel. The method further includes receiving a further network packet including a further payload. The method continues with determining, based on the payload and the further payload, an error vector. The method includes generating, based on the error vector, a plurality of indices. An index of the plurality of indices corresponds to a portion of a plurality of non-overlapping portions of the payload. The method further continues with selecting, based on the error vector, at least one index from the plurality of indices. The method includes sending, to the receiver via the communication channel, a further network packet. The further network packet includes the selected index and a portion of the payload corresponding to the selected index.

Abstract: Provided are systems and methods for adaptive payload extraction and retransmission in wireless data communications. An example method commences with transmitting a network packet to a receiver via a communication channel. The method further includes receiving a further network packet including a further payload. The method continues with determining, based on the payload and the further payload, an error vector. The method includes generating, based on the error vector, a plurality of indices. An index of the plurality of indices corresponds to a portion of a plurality of non-overlapping portions of the payload. The method further continues with selecting, based on the error vector, at least one index from the plurality of indices. The method includes sending, to the receiver via the communication channel, a further network packet. The further network packet includes the selected index and a portion of the payload corresponding to the selected index.

Abstract: Provided are systems and methods for convergent error vector indexing and retransmission in wireless data verifications. An example method includes transmitting a network packet to a receiver; receiving a further network packet being a copy of the network packet as received by the receiver, determining, based on the network packet and the further network packet, an error vector and locations of errors in the further network packet; sending, to the receiver, a first indexing packet including the locations of the errors; receiving a second indexing packet being a copy of the first indexing packet as received by the receiver; determining, based on the error vector and the second indexing packet, the locations of the errors in the second indexing packet; and sending a third indexing packet including the locations of the errors to the receiver, where the receiver corrects the further network packet using the third indexing packet.

Abstract: Systems and methods for artificial intelligence discovered codes are described herein. A method includes obtaining received samples from a receive decoder, obtaining decoded bits from the receive decoder based on the receiver samples, training an encoder neural network of a transmit encoder, the encoder neural network receiving parameters that comprise the information bits, the received samples, and the decoded bits. The encoder neural network is optimized using a loss function applied to the decoded bits and the information bits to calculate a forward error correcting code.

Abstract: Systems and methods for utilizing dynamic codes in a dynamic system comprising neural networks are disclosed. In an exemplary embodiment, training data is transmitted to an encoder block, the encoder block having an encoder neural network. Training data is encoded utilizing the encoder neural network of the encoder block, and then decoded by a decoder block, the decoder block having a decoder neural network. An end-end error is determined by comparing the training data that was transmitted to the encoder block against the decoded training data that was received from the decoder block. Encoder/decoder parameters to minimize the end-end error are optimized and transmitted. Upon receipt of the encoder/decoder parameter updates, the encoder block and the decoder block are initialized.

Abstract: A drilling system includes a sensor, an encoder operably connected to the sensor and a pressure pulse generator operably connected to the encoder. The pressure pulse generator is configured to produce a primary signal in response to input from the encoder. The drilling system further includes a primary transducer, a reference transducer and a signal processor connected to the primary transducer and the reference transducer. The signal processor includes a two-stage filter that is configured to extract the primary signal from noise observed at the primary transducer.

Abstract: A drilling system includes a sensor, an encoder operably connected to the sensor and a pressure pulse generator operably connected to the encoder. The pressure pulse generator is configured to produce a primary signal in response to input from the encoder. The drilling system further includes a primary transducer, a reference transducer and a signal processor connected to the primary transducer and the reference transducer. The signal processor includes a two-stage filter that is configured to extract the primary signal from noise observed at the primary transducer.