Techniques for implementing a performance-adaptive sampling strategy towards fast and accurate graph neural networks are provided. In one technique, a graph that comprises multiple nodes and edges connecting the nodes is stored. An embedding for each node is initialized, as well as a sampling policy for sampling neighbors of nodes. One or more machine learning techniques are used to train a graph neural network and learn embeddings for the nodes. Using the one or more machine learning techniques comprises, for each node: (1) selecting, based on the sampling policy, a set of neighbors of the node; (2) based on the graph neural network and embeddings for the node and the set of neighbors, computing a performance loss; and (3) based on a gradient of the performance loss, modifying the sampling policy.

A neural transformer model with attention is trained to predict candidates to complete a line of source code with a zero-inference capability. The model is trained on an unsupervised training dataset that includes features from source code written in multiple programming languages. The features include a file-level context and a local context, where the file-level context includes a global context, a class context, a function context, and/or a method context for each class, function and/or method of the source code programs used in the training dataset. The local context includes method bodies, function bodies, and/or stand-alone code of main method routines. From these features, the model is able to learn to predict an ordered sequence of code elements that complete a line of source code in a programming language seen and not seen during training.

A neural transformer model with attention is trained to predict candidates to complete a line of source code with a zero-inference capability. The model is trained on an unsupervised training dataset that includes features from source code written in multiple programming languages. The features include a file-level context and a local context, where the file-level context includes a global context, a class context, a function context, and/or a method context for each class, function and/or method of the source code programs used in the training dataset. The local context includes method bodies, function bodies, and/or stand-alone code of main method routines. From these features, the model is able to learn to predict an ordered sequence of code elements that complete a line of source code in a programming language seen and not seen during training.

A computer-implemented method for reliably identifying objects in a sequence of input images received with the aid of an imaging sensor, positions of light sources in the respective input image being ascertained from the input images in each case with the aid of a first machine learning system, in particular, an artificial neural network, and objects from the sequence of input images being identified from the resulting sequence of positions of light sources, in particular, with the aid of a second machine learning system, in particular, with the aid of an artificial neural network.

A device, computer program and computer-implemented method for machine learning. The method comprises providing a task comprising an action space of a multi-armed bandit problem or a contextual bandit problem and a distribution over rewards that is conditioned on actions, providing a hyperprior, wherein the hyperprior is a distribution over the action space, determining, depending on the hyperprior, a hyperposterior for that a lower bound for an expected reward on future bandit tasks has as large a value as possible, when using priors sampled from the hyperposterior, and wherein the hyperposterior is a distribution over the action space.

A method is provided for generating a visualization for explaining a behavior of a machine learning (ML) model. In the method, an image is input to the ML model for an inference operation. The input image has an increased resolution compared to an image resolution the ML model was intended to receive as an input. A resolution of a plurality of resolution-independent convolutional layers of the neural network are adjusted because of the increased resolution of the input image. A resolution-independent convolutional layer of the neural network is selected. The selected resolution-independent convolutional layer is used to generate a plurality of activation maps. The plurality of activation maps is used in a visualization method to show what features of the image were important for the ML model to derive an inference conclusion. The method may be implemented in a computer program having instructions executable by a processor.

The present disclosure relates to systems, methods, and non-transitory computer readable media for selecting hyper-parameter sets by utilizing a modified Bayesian optimization approach based on a combination of accuracy and training efficiency metrics of a machine learning model. For example, the disclosed systems can fit accuracy regression and efficiency regression models to observed metrics associated with hyper-parameter sets of a machine learning model. The disclosed systems can also implement a trade-off acquisition function that implements an accuracy-training efficiency balance metric to explore the hyper-parameter feature space and select hyper-parameters for training the machine learning model considering a balance between accuracy and training efficiency.

A device may receive a classification model generated based on a set of spectroscopic measurements performed by a first spectrometer. The device may store the classification model in a data structure. The device may receive a spectroscopic measurement of an unknown sample from a second spectrometer. The device may obtain the classification model from the data structure. The device may classify the unknown sample into a Kosher or non-Kosher group or a Halal or non-Halal group based on the spectroscopic measurement and the classification model. The device may provide information identifying the unknown sample based on the classifying of the unknown sample.

Embodiments are directed to neural network processing for multi-object three-dimensional (3D) modeling. An embodiment of a computer-readable storage medium includes executable computer program instructions for obtaining data from multiple cameras, the data including multiple images, and generating a 3D model for 3D imaging based at least in part on the data from the cameras, wherein generating the 3D model includes one or more of performing processing with a first neural network to determine temporal direction based at least in part on motion of one or more objects identified in an image of the multiple images or performing processing with a second neural network to determine semantic content information for an image of the multiple images.

Disclosed herein are methods for training and deploying a predictive model for generating a prediction, e.g., patient eligibility for a CAR-T therapy. Datasets, such as open healthcare claims datasets, may be missing data. Missing data may hamper the ability to generate sufficient information needed for training a predictive model. Methods include leveraging comprehensive datasets, such as closed claims datasets, to create training examples for input into a machine learning algorithm. In various embodiments, the comprehensive dataset is modified to simulate the data missingness in the target dataset; then, the modified dataset is paired with the ground truth label derived from the comprehensive dataset to create training examples. In various embodiments, a comprehensive dataset is paired with a target dataset to create training examples. After training a predictive model on such examples, the model can be deployed to make predictions in the target dataset even in light of missing data.