International Business Machines Corporation

Srihari Sridharan

Komminist S Weldemariam

Meenal Pore

Shelby Solomon Darnell

Solomon Assefa

Celia Cintas

Skyler Speakman

Nelson Kibichii Bore

Victor Abayomi Akinwande

Isaac Markus Serfaty

Geoffrey Henry Siwo

An illustrative embodiment includes a method for detecting whether a given item within input data is anomalous. The method includes: extracting activations at respective nodes of an autoencoder trained on the data, the activations comprising activations at the respective nodes for the given item within the data and for one or more other items within the data; calculating p-values corresponding to the respective nodes, wherein the p-value for a given node represents a proportion of the activations at the given node for the other items which are greater than the activations at the given node for the given item; determining at least one score at least in part by scanning for a subset of the respective nodes which maximizes a statistical scoring function applied to the corresponding p-values; and providing a visualization of at least the given item within the input data to a human user.

Identifying adversarial attacks with advanced subset scanning

A first set of user data is received and a user profile is constructed based on the user data and in accordance with a sensitive service involving the user. A situational context is analyzed based on the first set of data. Personalized questions are generated, responsive to the user profile and to the situational context. The personalized questions are presented to a user corresponding to the user data and responses to same are received, including detection of user micro-expressions. The responses are analyzed, according to one or more machine learning models. A neural network model selects an action to be performed in response to analyzing the responses from the user; the action is a sensitive service involving the user. An apparatus is triggered to send a simple message service (SMS) message to a point of care service professional; the message recommends performance of the sensitive service on the user.

Enhanced user screening for sensitive services

Representative features representing actions and states described in text corpus comprising unstructured natural language data are generated. State properties associated with the states from the representative features and action properties associated with the actions from the representative features are generated. A state transition matrix with initial configurations is generated based on the state space and action space properties. A computer environment is bootstrapped based on the state space, the action space and the initial state transition matrix.

Generating game environments from unstructured textual corpus for reinforcement learning

Methods and systems for generating a multichannel audio object. One or more features in a given video frame are identified using one or more image analysis neural networks. A multichannel audio object is generated based on the one or more identified features and one or more baseline audio tracks using an audio neural network.

Spatial-based audio object generation using image information

Image data is run through a neural network, and the neural network produces a vector representation of the image data. Random sparse sampling masks are created. The vector representation of the image data is masked with each of the random sparse sampling masks, the masking generating corresponding sparsely sampled vectors. The sparsely sampled vectors are transmitted to nodes of a consensus network, wherein a sparsely sampled vector of the sparsely sampled vectors is transmitted to a node of the consensus network. Votes from the nodes of the consensus network are received. Whether a consensus is achieved in the votes is determined. Responsive to determining that the consensus is achieved, at least one of identification and verification of the image data may be provided.

Growing community of inventors

Nairobi, Kenya

Srihari Sridharan