Disclosed is a quotation method executed by a computer, comprising: obtaining structure parameters and electrical parameters of a product (S101); constructing an external view of the product by using the structure parameters of the product, and performing similarity comparison on the external view of the product and the external view of a historical product to obtain an appearance similarity sorting (102); performing similarity comparison on the electrical parameters of the product and the electrical parameters of the historical product to obtain an electrical parameter similarity sorting (103); on the basis of the cost weights of a structural member and an electrical component and the appearance similarity sorting and the electrical parameter similarity sorting, obtaining a comprehensive sorting which is based on the structure parameters and the electrical parameters (S104); and determining, based on the comprehensive sorting, a bill of materials of the product, and calculating, based on the bill of the materials of the product, the product quotation (105).

Machine learning adversarial campaign mitigation on a computing device. The method may include deploying an original machine learning model in a model environment associated with a client device; deploying a classification monitor in the model environment to monitor classification decision outputs in the machine learning model; detecting, by the classification monitor, a campaign of adversarial classification decision outputs in the machine learning model; applying a transformation function to the machine learning model in the model environment to transform the adversarial classification decision outputs to thwart the campaign of adversarial classification decision outputs; determining a malicious attack on the client device based in part on detecting the campaign of adversarial classification decision outputs; and implementing a security action to protect the computing device against the malicious attack.

A method for determining an output token includes predicting a first probability of each of candidate output tokens of a first model, predicting a second probability of each of the candidate output tokens of a second model interworking with the first model, adjusting the second probability of each of the candidate output tokens based on the first probability, and determining the output token among the candidate output tokens based on the first probability and the adjusted second probability.

Methods, systems, and non-transitory machine-readable mediums for ranking on an absolute scale include displaying, on an electronic display, a first handle, a second handle, and an interactor, determining a value of the first handle and a value of the second handle based on their respective positions on the interactor, in response to a user dragging the first and second handles on the interactor, and determining a rank of the first and second handles based on the values of the first and second handles, in response to the user dragging the first and second handles on the interactor.

Intelligent reframing techniques are described in which content (e.g., a movie) can be generated in a different aspect ratio than previously provided. These techniques include obtaining various video frames having a first aspect ratio. Various objects can be identified within the frames. An object having the highest degree of importance in a frame can be selected and a focal point can be calculated based at least in part on that object. A modified version of the content can be generated in a second aspect ratio that is different from the first aspect ratio. The modified version can be generated using the focal point calculated based on the object having the greatest degree of importance. Using these techniques, the content can be provided in a different aspect ratio while ensuring that the most important features of the frame still appear in the new version of the content.

This disclosure provides methods and systems for predicting missing links and previously unknown numerals in a knowledge graph. A jointly trained multi-task machine learning model is disclosed for integrating a symbolic pipeline for predicting missing links and a regression numerical pipeline for predicting numerals with prediction uncertainty. The two prediction pipelines share a jointly trained embedding space of entities and relationships of the knowledge graph. The numerical pipeline additionally includes a second-layer multi-task regression neural network containing multiple regression neural networks for parallel numerical prediction tasks with a cross stich network allowing for information/model parameter sharing between the various parallel numerical prediction tasks.

A sensor data processing system and method is described. Contemplated systems and methods derive a first recognition trait of an object from a first data set that represents the object in a first environmental state. A second recognition trait of the object is then derived from a second data set that represents the object in a second environmental state. The sensor data processing systems and methods then identifies a mapping of elements of the first and second recognition traits in a new representation space. The mapping of elements satisfies a variance criterion for corresponding elements, which allows the mapping to be used for object recognition. The sensor data processing systems and methods described herein provide new object recognition techniques that are computationally efficient and can be performed in real-time by the mobile phone technology that is currently available.

A mechanism is described for facilitating smart convolution in machine learning environments. An apparatus of embodiments, as described herein, includes one or more processors including one or more graphics processors, and detection and selection logic to detect and select input images having a plurality of geometric shapes associated with an object for which a neural network is to be trained. The apparatus further includes filter generation and storage logic (“filter logic”) to generate weights providing filters based on the plurality of geometric shapes, where the filter logic is further to sort the filters in filter groups based on common geometric shapes of the plurality of geographic shapes, and where the filter logic is further to store the filter groups in bins based on the common geometric shapes, wherein each bin corresponds to a geometric shape.

A mechanism is described for facilitating smart convolution in machine learning environments. An apparatus of embodiments, as described herein, includes one or more processors including one or more graphics processors, and detection and selection logic to detect and select input images having a plurality of geometric shapes associated with an object for which a neural network is to be trained. The apparatus further includes filter generation and storage logic (“filter logic”) to generate weights providing filters based on the plurality of geometric shapes, where the filter logic is further to sort the filters in filter groups based on common geometric shapes of the plurality of geographic shapes, and where the filter logic is further to store the filter groups in bins based on the common geometric shapes, wherein each bin corresponds to a geometric shape.

The present disclosure relates to an object selection system that accurately detects and optionally automatically selects user-requested objects (e.g., query objects) in digital images. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of a query object. In particular, the object selection system can identify both known object classes as well as objects corresponding to unknown object classes.