Abstract: Low latency search for nearest neighbors in a dataset containing a large number of entries is improved using an error correction code (ECC) for partitioning data into clusters and retrieval. During initialization and preprocessing a d-dimensional space with clusters corresponding to ECC codewords is specified. Entries in the dataset are embedded into this space and associated with respective codewords, each codeword specifying a cluster. An index associates the codewords, clusters, and entries. During a query of the dataset, a query entry is processed to determine a query embedding in the d-dimensional space. The query embedding is used as input for a list decoder of the ECC. The list decoder provides a set of nearest codewords, with those codewords representing a set of candidate clusters that may contain nearest neighbors. The dataset entries associated with the candidate clusters may then be searched to determine query results comprising specific entries.

Abstract: Devices and techniques are generally described for adaptive targeting for voice notifications. In various examples, first data representing a predicted likelihood that a first user will interact with first content within a predefined amount of time may be received. A first set of features including features related to past voice notifications sent to the first user may be determined. A second set of features including features related to interaction with the first content when past voice notifications were sent may be received. A first machine learning model may generate a prediction that a voice notification will increase a probability that the first user interacts with the first content based on the first data, the first set of features, and the second set of features. Audio data comprising the voice notification may be sent to a first device associated with the first content.

Abstract: Systems and methods are described for mitigating errors introduced during processing of user input such as voice input. A query may be derived from processed user input. A performance predictor analyzes the query and uses historical data to predict whether the query will return relevant results if executed. If the query's predicted performance is below a threshold, a query rewriter may identify potential alternatives to the query from a library of “known good” queries. Different analyzers may be applied to identify different sets of alternatives, and machine learning models may be applied to rank the outputs of the analyzers. The best-matching alternatives from each analyzer may then be provided as inputs to a further machine learning model, which assesses the probability that each of the identified alternatives reflects the intent of the user. A most likely alternative may then be selected to execute in place of the original query.

Abstract: There is provided a method of sequential list decoding of an error correction code (ECC) utilizing a decoder comprising a plurality of processors. The method comprises: a) obtaining an ordered sequence of constituent codes usable for the sequential decoding of the ECC; b) executing, by a first processor, a task of decoding a first constituent code, the executing comprising: a. generating decoding candidate words (DCWs) usable to be selected for decoding a subsequent constituent code, each DCW associated with a ranking; b. for the first constituent code, upon occurrence of a sufficiency criterion, and prior to completion of the generating all DCWs and rankings, selecting, in accordance with a selection criterion, at least one DCW; c) executing, by a second processor, a task of decoding a subsequent constituent code, the executing comprising processing data derived from the selected DCWs to generate data usable for decoding a next subsequent constituent code.

Abstract: There is provided a method of obtaining one or more parity symbols (PS) of an encoding of information symbols (IS) according to a linear cyclic code, the method comprising: upon a permutation of information symbols (IS), generating data indicative of parity coefficients of a row of a generator matrix associated with the linear cyclic code, computing, for each given parity coefficient, a first data in accordance with, at least, the given parity coefficient and the first IS; updating, by the processing circuitry, for each given parity coefficient of the one or more parity coefficients, the first data, in accordance with, at least, the given parity coefficient and the respective IS; and upon meeting a parity completion criterion for a given parity coefficient, deriving a parity symbol from the respective first data, thereby obtaining the one or more parity symbols of the codeword of the linear cyclic code.

Abstract: There is provided a method of sequential list decoding of an error correction code (ECC) utilizing a decoder comprising a plurality of processors. The method comprises: a) obtaining an ordered sequence of constituent codes usable for the sequential decoding of the ECC; b) executing, by a first processor, a task of decoding a first constituent code, the executing comprising: a. generating decoding candidate words (DCWs) usable to be selected for decoding a subsequent constituent code, each DCW associated with a ranking; b. for the first constituent code, upon occurrence of a sufficiency criterion, and prior to completion of the generating all DCWs and rankings, selecting, in accordance with a selection criterion, at least one DCW; c) executing, by a second processor, a task of decoding a subsequent constituent code, the executing comprising processing data derived from the selected DCWs to generate data usable for decoding a next subsequent constituent code.

Abstract: There is provided a method of obtaining one or more parity symbols (PS) of an encoding of information symbols (IS) according to a linear cyclic code, the method comprising: upon a permutation of information symbols (IS), generating data indicative of parity coefficients of a row of a generator matrix associated with the linear cyclic code, computing, for each given parity coefficient, a first data in accordance with, at least, the given parity coefficient and the first IS; updating, by the processing circuitry, for each given parity coefficient of the one or more parity coefficients, the first data, in accordance with, at least, the given parity coefficient and the respective IS; and upon meeting a parity completion criterion for a given parity coefficient, deriving a parity symbol from the respective first data, thereby obtaining the one or more parity symbols of the codeword of the linear cyclic code.