International Business Machines Corporation

Harvard College

Patrick Lustenberger

Frederik Frank Flöther

Andrea Giovannini

Stefan Ravizza

David Ocheltree

Shikhar Kwatra

Thomas J Brunschwiler

Jennifer Ann Lewis

David B Kolesky

Mark Andrew Skylar-Scott

Saurabh Yadav

Kimberly A Homan

Adam Ivankay

Matthias Biniok

Sebastien G M Uzel

Katharina Theresa Kroll

Georgios Chaloulos

David Mesterhazy

Eric Slottke

Thomas Pfeiffer

Sebastien GM Uzel

A processor may gather raw data comprising a plurality of characteristic data samples of a target user group. The processor may categorize the characteristic data samples into a plurality of user-related classes and triggers. The processor may build an input property graph for each characteristic data sample. The processor may augment the input property graph by a concept of hierarchies. The processor may determine a modification vector from the augmented input property graph. The processor may train an encoder/decoder combination machine-learning system. An embedding vector and a modification vector are used as input for the decoder to build a trained machine-learning generative model.

Modification and generation of conditional data

In an approach, a processor creates a multi-layered knowledge graph (KG), wherein a first layer is a core KG, a second layer has application-specific structured facts, and a third layer has individualized facts. A processor adapts weights in each layer of the multi-layered KG based on the individualized facts. A processor uses, as input data to the multi-layered KG, individual environmental data. A processor maps the input data to the multi-layered KG in a sequence of the first layer, the second layer, and the third layer. A processor selects, as relevant nodes in the first layer and the second layer, the relevant nodes lying on a selected path from the input data via the first layer, the second layer, and the third layer having the highest average weight value along the selected path. A processor outputs facts of the relevant nodes from the first layer and the second layer.

Environment augmentation based on individualized knowledge graphs

Described are methods for producing multi-layered tubular tissue structures, tissue structures produced by the methods, and their use.

Methods of producing multi-layered tubular tissue constructs

A computer-implemented method for classification of data by a machine learning system using a logic constraint for reducing a data labeling requirement. The computer-implemented method includes: generating a first embedding space from a first partially labeled training data set, wherein in the first embedding space, content-wise related training data of the first partially labeled training data are clustered together, determining at least two clusters in the first embedding space formed from the first partially labeled training data, and training a machine learning model based, at least in part, on a second partially labeled training data set and the at least two clusters, wherein the at least two clusters are used as training constraints.

Semi-supervised learning with group constraints

A computer-implemented method for generating a group of representative model cases for a trained machine learning model may be provided. The method comprising determining an input space, determining an initial plurality of model cases, and expanding the initial plurality of model cases by stepwise modifying field values of the records representing the initial plurality of model cases resulting in an exploration set of model cases. Additionally, the method comprises obtaining a model score value for each record of the exploration set of model cases, continuing the expansion of the exploration set of model cases thereby generating a refined model case set, and selecting the records in the refined model case set based on relative record distance values and related model score values between pairs of records, thereby generating the group of representative model cases.

Artificial intelligence transparency

A method for personalizing a message between a sender and a receiver is provided. The method comprises semantically analyzing a communication history to form a knowledge graph, deriving formality level values using a first trained ML model, analyzing parameter values of replies to determine receiver impact score, and training a second ML system to generate a model to predict the receiver impact score value. The method also comprises selecting a linguistic expression in a message being drafted, determining an expression intent, modifying the linguistic expression based on the formality level and the expression intent to generate a modified linguistic expression, and testing whether the modified linguistic expression has an increased likelihood of a higher receiver impact score. The method also comprises repeating selecting the linguistic expression, determining the expression intent, modifying the linguistic expression, and testing until a stop criterion is met.

Communication content tailoring

Aspects of the present invention disclose a method for verifying labels of records of a dataset. The records comprise sample data and a related label out of a plurality of labels. The method includes one or more processors dividing the dataset into a training dataset comprising records relating to a selected label and an inference dataset comprising records with sample data relating to the selected label and all other labels out of the plurality of labels. The method further includes dividing the training dataset into a plurality of learner training datasets that comprise at least one sample relating to the selected label. The method further includes training a plurality of label-specific few-shot learners with one of the learner training datasets. The method further includes performing inference by the plurality of trained label-specific few-shot learners on the inference dataset to generate a plurality of sets of predicted label output values.

Data label verification using few-shot learners

Growing community of inventors

Herrliberg, Switzerland

Patrick Lustenberger