Techniques are provided for selection of machine learning algorithms based on performance predictions by trained algorithm-specific regressors. In an embodiment, a computer derives meta-feature values from an inference dataset by, for each meta-feature, deriving a respective meta-feature value from the inference dataset. For each trainable algorithm and each regression meta-model that is respectively associated with the algorithm, a respective score is calculated by invoking the meta-model based on at least one of: a respective subset of meta-feature values, and/or hyperparameter values of a respective subset of hyperparameters of the algorithm. The algorithm(s) are selected based on the respective scores. Based on the inference dataset, the selected algorithm(s) may be invoked to obtain a result. In an embodiment, the trained regressors are distinctly configured artificial neural networks. In an embodiment, the trained regressors are contained within algorithm-specific ensembles. Techniques are also provided for optimal training of regressors and/or ensembles.

An object identification and collection method is disclosed. The method includes receiving a pick-up path that identifies a route in which to guide an object-collection system over a target geographical area to pick up objects, determining a current location of the object-collection system relative to the pick-up path, and guiding the object-collection system along the pick-up path over the target geographical area based on the current location. The method further includes capturing images in a direction of movement of the object-collection system along the pick-up path, identifying a target object in the images; tracking movement of the target object through the images, determining that the target object is within range of an object picker assembly on the object-collection system based on the tracked movement of the target object, and instructing the object picker assembly to pick up the target object.

Disclosed herein are systems and methods for correlating item data. A system for correlating item data may comprise a memory storing instructions and at least one processor configured to execute instructions to perform operations comprising: receiving reference text data associated with a reference item from a device; receiving reference image data associated with the reference item from the remote device; determining candidate text data and candidate image data associated with at least one candidate item; selecting a text correlation model; determining a first similarity score by applying the text correlation model to the reference text data and the candidate text data; selecting an image correlation model; determining a second similarity score by applying the image correlation model to the reference image data and the candidate image data; calculating a confidence score based on the first and second similarity scores; and performing a responsive action based on the calculated confidence score.

There are provided a learning apparatus, a learning method, and a program that enable, by using one type of device data, learning of a plurality of models using different data formats. A learning data acquiring section (36) acquires first data that is first-type device data. A first learning section (42) performs learning of a first model (34(1)) in which an estimation using the first-type device data is executed by using the first data. A learning data generating section (40) generates second data that is second-type device data the format of which differs from the format of the first-type device data on the basis of the first data. A second learning section (44) performs learning of a second model (34(2)) in which an estimation using the second-type device data is executed by using the second data.

A model analyzer may receive a representative data set as input and select one of a plurality of analytic models to perform the analysis. Before deciding which model to use the model may be trained, and the trained model evaluated for accuracy. However, some models are known to behave poorly when the training data is distributed in a particular way. Thus, the cost of training a model and evaluating the trained model can be avoided by first analyzing the distribution of the representative data. Identifying the representative data distribution allows ruling out use of models for which the distribution of the representative data is unsuitable. Only models that may be compatible with the distribution of the representative data may be trained and evaluated for accuracy. The most accurate trained model whose accuracy meets an accuracy threshold may be selected to analyze subsequently received data related to the representative data.

A method includes receiving a request from a vehicle to perform a computing task, selecting a machine learning model from among a plurality of machine learning models based at least in part on the request, and predicting an amount of computing resources needed to perform the computing task using the selected machine learning model.

Various embodiments are provided for automating decision making for a neural architecture search by one or more processors in a computing system. One or more specifications may be automatically selected for a dataset, tasks, and one or more constraints for a neural architecture search. The neural architecture search may be performed based on the one or more specifications. A deep learning model may be suggested, predicted, and/or configured for the dataset, the tasks, and the one or more constraints based on the neural architecture search.

A method of processing test execution logs to determine error location and source includes creating a set of training examples based on previously processed test execution logs, clustering the training examples into a set of clusters using an unsupervised learning process, and using training examples of each cluster to train a respective supervised learning process to label data where each generated cluster is used as a class/label to identify the type of errors in the test execution log. The labeled data is then processed by supervised learning processes, specifically a classification algorithm. Once the classification model is built it is used to predict the type of the errors in future/unseen test execution logs. In some embodiments, the unsupervised learning process is a density-based spatial clustering of applications with noise clustering application, and the supervised learning processes are random forest deep neural networks.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing virtual surveillance windows for video surveillance. The methods, systems, and apparatus include actions of obtaining an original video, generating a downscaled video from the original video, detecting a first event at a location from the downscaled video using a first classifier, generating a windowed video from the original video based on the location, detecting a second event from the windowed video, and performing an action in response to detecting the second event.

In one aspect, an example methodology implementing the disclosed techniques includes, by an eco fees classification service, receiving information regarding a product to classify and generating a feature vector for the product, the feature vector representing a plurality of relevant features determined from the information regarding the product to classify. The method also includes, by the eco fee classification service, predicting, using an eco fees classification engine, a commodity classification for the product based on the feature vector, and recommending the commodity classification for the product for use in determining an eco fee to apply to a sale of the product. In some aspects, the method may also include computing the eco fee to apply to the sale of the product based on the recommended commodity classification.