The present disclosure is directed towards methods and systems for determining multimodal image edits for a digital image. The systems and methods receive a digital image and analyze the digital image. The systems and methods further generate a feature vector of the digital image, wherein each value of the feature vector represents a respective feature of the digital image. Additionally, based on the feature vector and determined latent variables, the systems and methods generate a plurality of determined image edits for the digital image, which includes determining a plurality of set of potential image attribute values and selecting a plurality of sets of determined image attribute values from the plurality of sets of potential image attribute values wherein each set of determined image attribute values comprises a determined image edit of the plurality of image edits.

Systems, apparatuses and methods may provide for technology that processes an inference workload in a first subset of layers of a neural network that prevents or inhibits data dependent branch operations, conducts an exit determination as to whether an output of the first subset of layers satisfies one or more exit criteria, and selectively bypasses processing of the output in a second subset of layers of the neural network based on the exit determination. The technology may also speculatively initiate the processing of the output in the second subset of layers while the exit determination is pending. Additionally, when the inference workloads include a plurality of batches, the technology may mask one or more of the plurality of batches from processing in the second subset of layers.

A method and apparatus of a device that classifies an image is described. In an exemplary embodiment, the device segments the image into a region of interest that includes information useful for classification and a background region by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.

In one embodiment, a device receives a request for a machine learning model to make an inference about input data included in the request. The device retrieves metadata regarding training data used to train the machine learning model from a ledger associated with the machine learning model. The device assesses bias of the machine learning model by comparing the input data in the request to the metadata from the ledger. The device provides an indication of the bias of the machine learning model for display.

In one embodiment, a device receives a request for a machine learning model to make an inference about input data included in the request. The device retrieves metadata regarding training data used to train the machine learning model from a ledger associated with the machine learning model. The device assesses bias of the machine learning model by comparing the input data in the request to the metadata from the ledger. The device provides an indication of the bias of the machine learning model for display.

Methods, apparatus, and processor-readable storage media for incorporating data into search engines using deep learning mechanisms are provided herein. An example computer-implemented method includes extracting one or more features from a search query by applying one or more machine learning algorithms to the search query; generating one or more word vectors by applying at least one deep learning technique to the one or more extracted features; mapping the one or more generated word vectors to one or more words from a corpus of data by implementing at least one deep similarity network; and outputting one or more results in response to the search query, wherein the one or more results are based at least in part on the one or more words from the corpus to which the one or more generated word vectors were mapped.

The technology disclosed relates to deduplicating metadata about places. A feature generator module is configured to generate features for metadata profiles. The metadata profiles represent a plurality of places. The features are based on geohash strings and word embeddings generated for the metadata profiles. A diff generator module is configured to generate diff vectors that pair-wise encode results of comparison between features of paired metadata profiles. A classification module is configured to generate similarity scores for the paired metadata profiles based on the diff vectors. A particular similarity score indicates whether metadata profiles in a particular pair of metadata profiles represent a same place.

Virtual game worlds for computer games can be provided using machine learning. The use of machine learning enables the virtual game worlds to be generated at run time by standard consumer hardware devices. Machine learning agents are trained in advance to the characteristics of the particular game world. Then, these suitably trained machine learning agents can be used to generate a relevant portion of a virtual game world, such as a portion of the virtual game world that is proximate to a play's position. Advantageously, the virtual game world can be provided in high resolution and is able to cover a substantially larger region than conventional practical.

A target location for a therapeutic intervention is determined in a subject with a neurological disorder. The target location is selected within at least one resting state network (RSN) map according to a predetermined criterion for the neurological disorder. The at least one RSN map includes a plurality of functional voxels within a brain of the subject, and each functional voxel of the plurality of functional voxels is associated with a probability of membership in an RSN. Instructions are transmitted to a treatment system that cause operation to be performed on the selected target location.

The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.