International Business Machines Corporation

Hui Wu

Aldis G Sipolins

Ravi Tejwani

Marco Cavallo

Jenna Reinen

Rogerio Schmidt Feris

Xiaoxiao Guo

Patrick D Watson

John Richard Smith

Noel C Codella

Rosario A Uceda-Sosa

Michele Merler

Yu Cheng

Hariklia Deligianni

Wei Zhang

Jonathan Hudson Connell, Ii

Nalini Kanta Ratha

Ulrich Alfons Finkler

Vince Siu

Rameswar Panda

Mayoore Selvarasa Jaiswal

An embodiment includes identifying an initial plurality of sets of hyperparameter values at which to evaluate an objective function that relates hyperparameter values to performance values of a neural network. The embodiment also executes training processes on the neural network with the hyperparameters set to the each of the initial sets of hyperparameter values such that the training process provides an initial set of the performance values for the objective function. The embodiment also generates an approximation of the objective function using splines at selected performance values. The embodiment approximates a point at which the approximation of the objective function reaches a maximum value, then determines an updated set of hyperparameter values associated with the maximum value. The embodiment then executes a runtime process using the neural network with the hyperparameters set to the updated set of hyperparameter values.

Configuring a neural network using smoothing splines

A system includes a virtual reality system configured to enable a user to interact with a virtual environment, a plurality of biofeedback sensors configured to monitor a user, and a computer system including a virtual reality module configured to generate at least a view of the virtual environment, a biofeedback module configured to fuse output of the plurality of biofeedback sensors with a plurality of events within the virtual environment, a training module configured to generate a model of user behavior, wherein the training module executed by the computer system enables the computer system to make a prediction of a user response of the user based on a corpus of biofeedback data, and an alert module configured to generate at least one alert to the user via the virtual reality system based on the user response predicted by the computer system.

Building a model based on responses from sensors

A method includes receiving input from a client at least partially specifying one or more characteristics, wherein the initial input includes a seed image and a natural language statement describing a desired change to the seed image; predicting one or more attributes of the seed image by operation of a neural network on the seed image; and parsing the natural language statement to identify desired changes to the one or more attributes of the seed image. The method also includes generating an interim target image by changing the one or more attributes of the seed image, according to the parsed natural language statement; selecting a set of images from an image database for output to the client, each of said set of images being determined to at least partially satisfy the one or more changed attributes of the seed image; and displaying the set of images to the client.

Dialog-based image retrieval with contextual information

A method includes detecting an eye movement of a reader during a reading of presented text; determining, based on whether an eye movement is detected, whether the reader is looking at the presented text; pausing a presentation of the presented text if it is determined that the reader is not looking at the presented text; and resuming, if the presentation of the text is paused, the presentation of the presented text.

Enhanced speed reading with eye tracking and blink detection

A search engine is modified to perform increasingly precise image searching using iterative Natural Language (NL) interactions. From an NL search input, the modification extracts a set of input features, which includes a set of response features corresponding to an NL statement in the NL search input and a set of image features from a seed image in the NL search input. The modification performs image analysis on an image result in a result set of a query including at least some of the input features. In a next iteration of NL interactions, at least some of the result set is provided. An NL response in the iteration is added to a cumulative NL basis, and a revised result set is provided, which includes a new image result corresponding to a new response feature extracted from the cumulative NL basis.

Image retrieval using interactive natural language dialog

A method includes: receiving initial input from a client at least partially specifying one or more characteristics sought by the client; selecting a set of images from an image database for output to the client; and determining after each set of images whether an end condition has occurred. The method also includes, until the end condition has occurred: responsive to each set of images output to the client, receiving additional input from the client further specifying the one or more characteristics sought by the client; and responsive to each input received from the client, selecting another set of images for presentation to the client, said set of images being determined to at least partially satisfy the one or more characteristics specified by all input received from the client, said determination being based at least in part on side information for respective images for at least the set of images.

A data presentation method through augmented reality, system, and computer program product include creating a file container for a presentation that supports raw data embedding and definition of available interactions and levels of confidentiality of information for the presentation, streaming presentation content from the file container to a plurality of augmented reality devices, and generating a personalized individual interactive experience of the presentation content for at least one person wearing an augmented reality device in the plurality of augmented reality devices.

Personalized interactive data presentation through augmented reality

Systems, computer-implemented methods, and computer program products to generate virtual motion sensor data from computer animations are provided. 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 tracker component that can track virtual location data corresponding to a feature of a computer animated character in a virtual environment. The computer executable components can further comprise a virtual motion sensor component that, based on the virtual location data, can generate virtual motion sensor data.

Virtual generation of labeled motion sensor data

A facial expression feedback system for providing real-time feedback on how closely a user matches his or her facial expression to a target expression is presented. The facial expression feedback system receives sensor data captured by a set of sensors. The facial expression feedback system evaluates the captured sensor data to generate a set of confidence scores with respect to a target facial expression. The system presents the feedback by modifying a multimedia presentation based on the generated set of confidence scores.

Facial mirroring in virtual and augmented reality

A virtual reality (VR) system for VR desk application that allows a user to move in a VR environment while sitting in front of a working desk is provided. The VR system receives sensor data from a mobile device. The VR system generates a set of sitting motion data by interpreting the received sensor data as a motion of a limb of a person in a sitting posture. The VR system maps the set of sitting motion data into a set of movements in the VR environment. The VR system renders the VR environment and presents the rendered VR environment.

Locomotion in virtual reality desk applications

Augmented reality speed reading is provided by detecting a reader's changing gaze direction; detecting movements of the reader's eye; and between movements of the reader's eye, displaying text at the reader's gaze direction. An exemplary apparatus includes an eye illuminator that delivers light to a reader's eye; an eyeward camera that generates digital images of the reader's eye including reflected light from the eye illuminator; a display; and a processor that is connected in communication with the eyeward camera and the display. The processor implements an eye tracking module that receives the digital images from the eyeward camera and detects the reader's gaze direction, and the processor implements a text display module that controls the display to present text at the reader's gaze direction.

Augmented reality speed reading

Product recommendations are provided to a target user that take into account the style, interests, and hobbies of the target user and a desire by the target user to be unique from the target user's social group. In some aspects, a list of recommended products may be generated for the target user based on data about the target user's purchasing habits, social media interactions, or any other data. A list of products associated with users in the target user's social group may also be generated, for example, based on products purchased, currently worn by, or previously worn by the users in the target user's social group. A uniqueness-aware list of recommended products may then be generated from the list of recommended products by removing any products found in both the list of recommended products and the list of products associated with users in the target user's social group.

Determination of unique items based on generating descriptive vectors of users

A method of displaying information relating to an allergen present in a food substance together with a user profile, the method including capturing an image of a scene, segmenting the image to determining at least a segmentation of the food substance in the image, determining a classification of the food substance using the segmentation, determining a presence of the allergen in the food substance using the classification of the food substance and a database of allergens and food substances, determining a risk to a user using the user profile specifying a user sensitivity to the allergen, and displaying an output including a view of the user profile and the image, wherein the image is augmented to identify the presence of the allergen.

Growing community of inventors

White Plains, NY, United States of America

Hui Wu