International Business Machines Corporation

Daniel Jakub Ryszka

Bartlomiej Tomasz Malecki

Blazej Rafal Rutkowski

Maria Hanna Oleszkiewicz

Lukasz Grzegorz Cmielowski

Wojciech Sobala

Gregory Bramble

Amadeusz Masny

Szymon Kucharczyk

Dorota Lączak

Disclosed herein is a method of training an artificial intelligence model that comprises an iterative training loop. Said iterative training loop comprises: receiving a current set of training data; dividing said current set of training data into a predetermined number of training data subsets; sequentially training said artificial intelligence model with each of said predetermined number of training data subsets using a training portion and calculating a performance metric using a validation portion; and comparing performance metrics from a previous iteration of said iterative training loop to said calculated performance metric to determine if an improving performance metric condition is met. Said method further comprises halting said iterative training loop unless said improving performance metric condition is not met at least once within a predetermined number of previous iterations.

Early stopping of artificial intelligence model training using control limits

The present disclosure relates to a computer-implemented method for generating a machine learning module (ML-module). The method comprises providing training data comprising a first set of data corresponding to a first feature and a second set of data corresponding to a second feature and generating a further set of data, wherein the further set of data corresponds to a further feature. A first correlation metric as a measure of a correlation between a selected feature of the first and the second feature and the further feature is calculated. Furthermore, a bias metric is determined indicating a strength of a bias of the trained ML-module towards a first subset of values of the further feature or a second subset of values of the further feature if the first correlation metric is greater than a first threshold. If the bias metric satisfies the bias constraint, then the ML-module is released for usage.

Controlling a bias of a machine learning module background

Systems and methods for composite storage of data across tiers of a multi-tenant storage device are provided. In embodiments, a method includes determining attributes associated with each query in a set of queries; determining whether each of the attributes meet respective predetermined threshold values for a first storage tier, a second storage tier and a third storage tier based on statistical data generated for the attributes; updating storage rules for at least one of the first storage tier, the second storage tier and the third storage tier based on the determining; receiving data from the tenant for storage; dividing the data into at least a first portion and a second portion based on the storage rules; and storing the at least the first portion and the second portion on separate ones of the first storage tier, the second storage tier and the third storage tier based on the storage rules.

Composite storage of objects in multi-tenant devices

A method, computer system, and a computer program product for providing reduced training data for training a machine learning model (ML-model) is disclosed. The present invention may include generating the reduced training data dependent on a first two batches of data records of original training data. The present invention may include generating an updated version of the reduced training data dependent on the reduced training data and a further batch of the original training data, wherein a size of the updated version of the reduced training data is equal or less than a size of the limited storage capacity and less than a combined size of the reduced training data and the further batch together. The reading of a further batch of the data records of the original training data and the generating of an updated version of the reduced training data may be repeated.

Providing reduced training data for training a machine learning model

A computer-implemented method for transferring data is provided. In an illustrative embodiment, the method includes retrieving, by a computer, an original dataset to be sent from a sender to a receiver. The method also includes generating, by the computer, a model based on at least a subset of the original dataset. The model generates a predicted dataset. The model is selected from a plurality of model types based on data complexity of the original dataset and a desired level of approximation of the predicted dataset to the original dataset. The method also includes transferring, by the computer, the model to the receiver. The receiver uses the model to generate the predicted dataset, wherein the predicted dataset matches the original dataset to a selected degree of approximation. Transfer of the model is quicker than transfer of the original dataset.

Transferring large datasets by using data generalization

A method for controlling exposure of sensitive data though a logging system is provided. The method comprises: upon receiving a request by the request handler, determining sensitive data as part of the request by applying a rule, converting the data into a transformed format, and registering the data together with a related data field label with a log handler. Then, upon receiving by the log handler a log entry, converting each expression of the log entry into the transformed format, and comparing each transformed expression with each of the sensitive data in the transformed format. Upon determining a match of one of the transformed expressions with one of the sensitive data in the transformed format, the method comprises issuing an alert indicating that the log entry comprises sensitive data.

Detecting sensitive data exposure via logging

A computer-implemented method of creating a log file is disclosed. The method comprises: storing a request of a service to be executed by a computer system, wherein the service is performed using multiple software methods; executing the service by providing the request to the computer system; detecting a failure of the service; performing a stack trace of the service to identify a subset of the multiple software methods; providing a source code for the subset of the multiple software methods; modifying the source code for the subset of the multiple software methods to add logging statements, wherein the logging statements are configured for generating log data; re-executing the service using the modified source code to generate the log data; and generating the log file from the log data.

Growing community of inventors

Cracow, Poland

Daniel Jakub Ryszka