Nvidia Corporation

King's College London

Wenqi Li

Daguang Xu

Andrew Feng

Yan Cheng

Fausto Milletari

Nicola Christin Rieke

Rong Ou

Sebastien Ourselin

Tom Vercauteren

Xiaosong Wang

Ali Hatamizadeh

Lickkong Tam

Wentao Zhu

Yuhong Wen

Can Zhao

Lucas Fidon

Charles Jonathan Hancox

Maximilian Baust

Kevin Frank Lu

Guotai Wang

Riddhish Bhalodia

Apparatuses, systems, and techniques to generate labeled training data. In at least one embodiment, labeled training images are generated from medial images annotated with natural language text.

Extending supervision using machine learning

Apparatuses, systems, and techniques to perform federated training of neural networks while maintaining control over dissemination of local models of neural networks from which aspects of local training data might be extracted. In at least one embodiment, a neural network is trained on local training data and a local model is provided to be aggregated with other local models into a global model that is in turn used for further local model training, wherein a provided local model or training is adjusted to reduce an ability to extract aspects of local training data therefrom.

Neural network trained using federated learning with local training data preserved at local edge circuits

Apparatuses, systems, and techniques to collaboratively train one or more machine learning models. Parameter reviewers may be configured to compare sets of machine learning model parameter information in order to generate one or more machine learning models, such as neural networks.

Processor and system to train machine learning models based on comparing accuracy of model parameters

A computer-implemented method for segmenting an input image, the method comprises: generating a first segmentation of the input image using a first machine learning system, the first segmentation comprising multiple segments; receiving, from a user, at least one indication, wherein each indication corresponds to a particular segment from the multiple segments, and indicates one or more locations of the input image as belonging to that particular segment; constructing, for each segment of the multiple segments having at least one corresponding indication, a respective geodesic distance map, based on the input image and the user indications received for that segment; and generating a second segmentation using a second machine learning system based on the input image and the constructed geodesic distance maps.

System and computer-implemented method for segmenting an image

Growing community of inventors

London, United Kingdom

Wenqi Li