A method comprises displaying, via an interactive interface, a medical scan and a plurality of prompts of each prompt decision tree of a plurality of prompt decision trees in succession, beginning with automatically determined starting prompts of each prompt decision tree, in accordance with corresponding nodes of each prompt decision tree until a leaf node of each prompt decision tree is ultimately selected. Labeling data indicating the ultimately selected leaf node of each prompt decision tree is determined for the medical scan.

A method of labeling a dataset of input samples for a machine learning task includes selecting a plurality of pre-trained machine learning models that are related to a machine learning task. The method further includes processing a plurality of input data samples through each of the pre-trained models to generate a set of embeddings. The method further includes generating a plurality of clusterings from the set of embeddings. The method further includes analyzing, by a processing device, the plurality of clusterings to extract superclusters. The method further includes assigning pseudo-labels to the input samples based on analysis.

Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Systems and methods are provided for enhanced pose generation based on generative modeling. An example method includes accessing an autoencoder trained based on poses of real-world persons, each pose being defined based on location information associated with joints, with the autoencoder being trained to map an input pose to a feature encoding associated with a latent feature space. Information identifying, at least, a first pose and a second pose associated with a character configured for inclusion in an in-game world is obtained via user input, with each of the poses being defined based on location information associated with the joints and with the joints being included on a skeleton associated with the character. Feature encodings associated with the first pose and the second pose are generated based on the autoencoder. Output poses are generated based on transition information associated with the first pose and the second pose.

A method and apparatus comprising generating a dynamic personalized webpage is disclosed. At least two webpages are loaded in a fashion that is hidden from the user. Content from the at least two webpages is extracted based on classification “of interest” by an artificial intelligence algorithm. A dynamic personalized webpage comprising extracted content is then generated and displayed to the user. In the preferred embodiment, the user's dynamic personalized webpage will be filled with advertisements tailored to the user and the user would receive at least some revenue from advertisements.

A system and method for analyzing images using programmable device is disclosed. A sequencer operating on the non-transitory programmable device applies the first image analysis step to the first image to develop annotated training data. Specifications of the first image and the first image analysis step are developed using a graphical user interface operating on a computer. In addition, a machine learning system trainer operating on the programmable device trains an untrained machine learning system to develop a trained machine learning system. When the trained machine learning system is presented with the first image as an input, the trained machine learning system develops a prediction of the annotated training data. In addition, the sequencer analyzes a second image by undertaking a workflow, wherein the workflow is received from the computer and is specified using the graphical user interface and comprises a second image analysis step that that specifies operating the trained machine learning system.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.

In embodiments of event image curation, a computing device includes memory that stores a collection of digital images associated with a type of event, such as a digital photo album of digital photos associated with the event, or a video of image frames and the video is associated with the event. A curation application implements a convolutional neural network, which receives the digital images and a designation of the type of event. The convolutional neural network can then determine an importance rating of each digital image within the collection of the digital images based on the type of the event. The importance rating of a digital image is representative of an importance of the digital image to a person in context of the type of the event. The convolutional neural network generates an output of representative digital images from the collection based on the importance rating of each digital image.

A computer-implemented method includes accessing social media data, wherein the social media data is associated with one or more profiles and corresponds to a venue. The computer-implemented method further includes determining sentiment information corresponding to each of the one or more profiles based on the social media data. The computer-implemented method further includes, for each of the one or more profiles: identifying a path through the venue, wherein the path represents at least one movement associated with the profile and associating the sentiment information with the path through the venue. The computer-implemented method further includes, responsive to associating the sentiment information with the path through the venue for each of the one or more profiles, identifying one or more trends. The computer-implemented method further includes presenting the one or more trends for review. A corresponding computer system and computer program product are also disclosed.

A computer-implemented tool for automated classification and interpretation of documents, such as life science documents supporting clinical trials, is configured to perform a combination of raw text, document construct, and image analyses to enhance classification accuracy by enabling a more comprehensive machine-based understanding of document content. The combination of analyses provides context for classification by leveraging relative spatial relationships among text and image elements, identifying characteristics and formatting of elements, and extracting additional metadata from the documents as compared to conventional automated classification tools, wherein natural language processing (NLP) is applied to associate text with tokens, and relevant differences and similarities between protocols are identified.