International Business Machines Corporation

University College Cork

Radu Marinescu

Akihiro Kishimoto

Adi Ionel Botea

Elizabeth Daly

Oznur Alkan

Yufang Hou

Alice-Maria Marascu

Charles Arthur Jochim

Vanessa Lopez Garcia

Hiroshi Kajino

Lea Deleris

Biplav Srivastava

Bei Chen

John Erik Wittern

Yunfeng Zhang

Matthew Scott Davis

Kartik Talamadupula

Parikshit Ram

Vera Liao

Carlos A Alzate Perez

Mattia Chiari

Peter Nicholas Wilson

Larisa Shwartz

Beat Buesser

Marco Luca Sbodio

Yassine Lassoued

Julien Monteil

Spyros Kotoulas

Amadou Ba

Michele Berlingerio

Sean A McKenna

Abdul Razak

Theodora Brisimi

Martin Wistuba

Eliezer Segev Wasserkrug

Bogdan Eugen Sacaleanu

Djallel Bouneffouf

Christian Muise

Ambrish Rwat

Masataro Asai

Fabrizio Cucci

Razak Abdul

A plurality of objectives is received for a given dataset for an automated machine learning (autoML) process. A set of tradeoffs for the plurality of objectives are received that distribute weights to respective objectives. Pipelines are provided for the dataset that optimize each of the plurality of objectives according to the set of tradeoffs.

AutoML with multiple objectives and tradeoffs thereof

Various embodiments are provided for intelligent resolution of conflicting information in a dialog system in a computing environment by a processor. Conflicting information relating to one or more queries may be detected between one or more users using the dialog system. One or more responses may be provided to resolve the conflicting information according to a knowledge domain.

Intelligent resolution of conflicting information in adaptive dialog systems

In an approach for building an automated customer support system, a processor receives a set of sentences extracted from a natural language conversation occurring between an IT support system and a user. A processor extracts an initial state and a goal state from the set of sentences using a Natural Language Classifier. A processor extracts one or more actions from the set of sentences. A processor creates a formal planning model. A processor determines the one or more formal actions are not complete using a first machine learning model. A processor completes the one or more formal actions with one or more missing parts. A processor produces an executable plan using a planner. A processor implements one or more executable scripts according to a sequence of the one or more formal actions of the executable plan using a plan executor.

Automated system for customer support

One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to facilitating code development by predicting one or more code attributes and/or code portions for use in a project code to be written. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a dialogue component that generates a query based on a natural language request comprising a code-related attribute, and a prediction component that predicts another attribute or a code portion to satisfy the request. In an embodiment, an input dataset employed to support the influence mapping can comprise time-stamped tuple data comprising a state, an action and a reward. The code-related attribute can at least partially define a project code, of code to be written.

Dialogue- and machine learning-facilitated code development

Techniques regarding generating and/or training one or more symbolic models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a training component that can train a symbolic model via active machine learning. The symbolic model can characterize a formal planning language for a planning domain as a plurality of digital image sequences.

Symbolic model training with active learning

One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to outputting an optimal decision policy base on informal knowledge input. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise an analysis component that analyzes an input dataset comprising a constraint in a natural language form, and an augmentation component that generates an influence mapping comprising a constraint variable based on the constraint input. In an embodiment, an input dataset employed to support the influence mapping can comprise time-stamped tuple data comprising a state, an action and a reward. In an embodiment, an inference engine can generate an output policy in response to the constraint input and which output policy can be based on the constraint input and constraint variable.

Knowledge augmented sequential decision-making under uncertainty

A method, system, and computer program product for learning parameters of Bayesian network using uncertain evidence, the method comprising: receiving input comprising graph representation and at least one sample of a Bayesian network, the graph comprising plurality of nodes representing random variables and plurality of directed edges representing conditional dependencies, wherein each of the at least one sample comprising for each node a value selected from the group consisting of: a known value; an unknown value; and an uncertain value; and applying on the input a Bayesian network learning process configured for calculating estimates of conditional probability tables of the Bayesian network using probabilities inferred by applying on the input a Bayesian network uncertain inference process configured for performing inference in a Bayesian network from uncertain evidence.

Learning parameters of Bayesian network using uncertain evidence

Embodiments for intelligent application scenario testing and error detection by a processor. One or more modified application scenarios may be automatically generated from an initial application scenario having configuration data and a plurality of operations relating to an error. The one or more modified application scenarios are variations of the initial application. The one or more modified application scenarios may be executed to detect the existence or non-existence of the error in the one or more modified application scenarios.

Intelligent application scenario testing and error detection

Various embodiments are provided for intelligent application of operational rules to operational data in a computing environment by a processor. One or more operational rules may be extracted and formalized from a knowledge graph, a domain knowledge, or a combination thereof describing one or more operational policies and conditions. The one or more operational rules may be applied to operational data to identify and filter non-compliant operational data.

Intelligent learning and application of operational rules

In an approach for recommending a safe path for people to navigate an environment, a processor generates a contact graph for a user in a group of users in an area, based on a pre-defined distance measurement between the user and another user in a same timestamp during a pre-defined time period. A processor builds a profile for the user based on the contact graph, the profile including a probability model corresponding to the contact graph to estimate an infection probability for the user. A processor calculates an initial route for the user from a first location to a second location in the area. A processor analyzes an infection risk for the user based on the profile and other users within a pre-defined distance to the user in the initial route. A processor updates the initial route based on the analysis to minimize the risk to be infected.

Safe zones and routes planning

In an approach to predictive contact tracing, a computer receives a query associated with contact tracing of a person with an infection. A computer retrieves timestamped location data associated with the person over a period of time. Based on the retrieved data, a computer creates a contact graph associated with the person, where the contact graph depicts one or more other people that were in contact with the person over the period of time. A computer retrieves medical data associated with the person and the one or more other people that were in contact with the person over the period of time. Based on the retrieved data, a computer builds a probabilistic model. A computer runs the probabilistic model to provide a prediction of a probability of infection of the one or more other people over the period of time as a result of being in contact with the person.

Predictive contact tracing

Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Facilitating answering questions involving reasoning over quantitative information

A historical log of a plurality of a type of Internet-connected appliances is collected. a dynamic probabilistic graphical model of the time-lined interactions between subsystems and components of the appliances is generated. The probabilistic graphical model is trained by applying machine learning techniques and applying expert knowledge. A natural language processing (NLP) conversational user interface for diagnostic queries regarding operational errors is provided, and responsive to receive a diagnostic query in a conversational format from a user regarding a particular type, make, and model of an appliance of the plurality of the type of Internet-connected appliances, a diagnostic response is provided to the user interface using the natural language processing conversational format.

Interactive diagnostics of connected appliance devices

A computer generates a formal planning domain description. The computer receives a first text-based description of a domain in an AI environment. The domain includes an action and an associated attribute, and the description is written in natural language. The computer receives the first text-based description of the domain and extracts a first set of domain actions and associated action attributes. The computer receives audio-visual elements depicting the domain, generates a second text-based description, and extracts a second set of domain actions and associated action attributes. The computer constructs finite state machines corresponding to the extracted actions and attributes. The computer converts the FSMs into a symbolic model, written in a formal planning language, that describes the domain.

Generating symbolic domain models from multimodal data

Systems, computer-implemented methods, and computer program products to facilitate automated generation of a machine learning pipeline based on a pipeline grammar are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a pipeline structure generator component that generates a machine learning pipeline structure based on a pipeline grammar. The computer executable components can further comprise a pipeline optimizer component that selects one or more machine learning modules that achieve a defined objective to instantiate a machine learning pipeline based on the machine learning pipeline structure.

Growing community of inventors

Dublin, Ireland

Radu Marinescu