Abstract: Approaches for data compression involve a compression circuit packing non-zero data elements of a succession of words of a plurality of blocks into packed words by packing non-zero data elements of one or more words of the succession in each packed word, and restricting each packed word to data elements of one uncompressed block. The compression circuit writes each packed word in a RAM and within a compressed address range associated with the uncompressed block when the packed word is full of non-zero data elements, or before the packed word is full if the next input word is of another uncompressed block.

Abstract: Approaches for data compression involve a compression circuit packing non-zero data elements of a succession of words of a plurality of blocks into packed words by packing non-zero data elements of one or more words of the succession in each packed word, and restricting each packed word to data elements of one uncompressed block. The compression circuit writes each packed word in a RAM and within a compressed address range associated with the uncompressed block when the packed word is full of non-zero data elements, or before the packed word is full if the next input word is of another uncompressed block.

Abstract: A method for de-prejudicing Artificial Intelligence (AI) based anomaly detection is disclosed. The method includes training and testing an AI model based on a labelled training data, determining whether the AI model reveals a bias, based on one or more prejudicing variables, and thereafter re-building the AI model based on iterative process of de-prejudicing the feature set of the AI model and de-prejudicing the training data. A check is made to determine whether the feature set of the AI model feature set includes any proxy variables associated with any of the prejudicing variables and identifies the weight to be assigned to a proxy variable based on the intra-cohort variation in separate machine learning models built for each cohort associated with each value of the prejudicing variable. The feature set of the AI model is de-prejudiced based on the explanatory power of the proxy variables independent of the prejudicing variables.

Abstract: A system includes a synchronizer circuit configured to monitor a first bus coupled between a memory and a first device to determine an occupancy threshold of the memory based on one or more write requests from the first device. The synchronizer circuit monitors a second bus between the memory and a second device to receive a first read transaction of a read request from the second device. The synchronizer circuit determines that the first read transaction is allowed to be sent to the memory based on the occupancy threshold of the memory. In response to the determination, the first read transaction is sent to the memory.

Abstract: A method for de-prejudicing Artificial Intelligence (AI) based anomaly detection is disclosed. The method includes training and testing an AI model based on a labelled training data, determining whether the AI model reveals a bias, based on one or more prejudicing variables, and thereafter re-building the AI model based on iterative process of de-prejudicing the feature set of the AI model and de-prejudicing the training data. A check is made to determine whether the feature set of the AI model feature set includes any proxy variables associated with any of the prejudicing variables and identifies the weight to be assigned to a proxy variable based on the intra-cohort variation in separate machine learning models built for each cohort associated with each value of the prejudicing variable. The feature set of the AI model is de-prejudiced based on the explanatory power of the proxy variables independent of the prejudicing variables.

Abstract: An organizational fraud detection (OFD) system and method for flagging one or more transactions as a potential fraudulent activity, in an organization is disclosed. The OFD system comprises: a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to: receive a suspected transaction for investigation, classify the suspected transaction into one or more groups of fraudulent activity; select, based on the classification, a set of investigation rules for investigating the suspected transaction; determine, based on data selection rules, the data associated with the suspected transaction; ascertain an accuracy score and an impact score associated with the suspected transaction; and classify the suspected transaction as a potential fraudulent activity on at least one of the accuracy score and the impact score exceeding a pre-defined threshold.