A device, a method and a computer program for training and/or verifying the robustness of an artificial neural network. The artificial neural network is designed to determine an output variable. The method includes: predefining an input variable for the network which has a plurality of dimensions,. For each dimension of the input variable or for each dimension of an output of a linear layer of the artificial neural network without an activation function to which the input variable is mapped by the artificial neural network, the method includes a determination of an upper input variable limit for which a disturbance variable model by which the input variable is able to be mapped to a disturbed input variable has the highest possible value in the dimension, and a determination of a lower input variable limit for which the disturbance variable model has the lowest value possible in the dimension.

A device, a method and a computer program for training and/or verifying the robustness of an artificial neural network. The artificial neural network is designed to determine an output variable. The method includes: predefining an input variable for the network which has a plurality of dimensions,. For each dimension of the input variable or for each dimension of an output of a linear layer of the artificial neural network without an activation function to which the input variable is mapped by the artificial neural network, the method includes a determination of an upper input variable limit for which a disturbance variable model by which the input variable is able to be mapped to a disturbed input variable has the highest possible value in the dimension, and a determination of a lower input variable limit for which the disturbance variable model has the lowest value possible in the dimension.

A computing system including a processing circuit in communication with a camera having a field of view. The processing circuit is configured to perform operations related to detecting, identifying, and retrieving objects disposed amongst a plurality of objects. The processing circuit may be configured to perform operations related to object recognition template generation, feature generation, hypothesis generation, hypothesis refinement, and hypothesis validation.

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.

A method includes: (A) receiving a selection of a 3D model stored in one or more memories, the 3D model corresponding to an object and (B) setting a camera parameter set for a camera for use in detecting a pose of the object in a real scene. The method also includes (C) generating at least one 2D synthetic image based at least on the camera parameter set by rendering the 3D model in a view range for generating training data.

A feature learning system (100) includes a similarity definition unit (101), a learning data generation unit (102), and a learning unit (103). The similarity definition unit (101) defines a degree of similarity between two classes related to two feature vectors, respectively. The learning data generation unit (102) acquires the degree of similarity, based on a combination of classes to which a plurality of feature vectors acquired as processing targets belong, respectively, and generates learning data including the plurality of feature vectors and the degree of similarity. The learning unit (103) performs machine learning using the learning data.

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.

A system and method for predicting mild cognitive impairment (MCI) related diagnosis and prognosis utilizing hybrid machine learning. More specifically, the system and method produce predictions of MCI conversions to dementia and prognosis related thereof. Using available medical imaging and non-imaging data a diagnosis and prognosis model is trained using transfer learning. A platform may then receive a request from a clinician for a target patient's diagnosis or prognosis. The target patient's medical data is retrieved and used to create a model for the target patient. Then details of the target patient's model and the diagnosis and prognosis model are compared, a prediction is generated, and the prediction is returned to the clinician. As new medical data becomes available it is fed into the respective model to improve accuracy and update predictions.

Aspects of the disclosure relate to determining perceptive range of a vehicle in real time. For instance, a static object defined in pre-stored map information may be identified. Sensor data generated by a sensor of the vehicle may be received. The sensor data may be processed to determine when the static object is first detected in an environment of the vehicle. A distance between the object and a location of the vehicle when the static object was first detected may be determined. This distance may correspond to a perceptive range of the vehicle with respect to the sensor. The vehicle may be controlled in an autonomous driving mode based on the distance.

A user-generated graphical representation can be sent into a generative network to generate a synthetic image of an area including a road, the user-generated graphical representation including at least three different colors and each color from the at least three different colors representing a feature from a plurality of features. A determination can be made that a discrimination network fails to distinguish between the synthetic image and a sensor detected image. The synthetic image can be sent, in response to determining that the discrimination network fails to distinguish between the synthetic image and the sensor-detected image, into an object detector to generate a non-user-generated graphical representation. An objective function can be determined based on a comparison between the user-generated graphical representation and the non-user-generated graphical representation. A perception model can be trained using the synthetic image in response to determining that the objective function is within a predetermined acceptable range.