A method serves for determining particles (3), in particular bacteria in fluid and operates using an imaging optical device with a light source (1), with an optical sensor (4) with a field of light-sensitive pixels and with a fluid sample, which is to be examined, arranged between the light source (1) and the sensor (4). Characteristics of at least one particle (3), which is detected with regard to imaging, are compared to characteristics of a characteristics collection for determining the detected particle (3). The image acquisition is effected with darkfield technology and a light-sensitive pixel comprises several subpixels which are used for image acquisition.

The embodiments describe a technique for customizing activation functions automatically, resulting in reliable improvements in performance of deep learning networks. Evolutionary search is used to discover the general form of the function, and gradient descent to optimize its parameters for different parts of the network and over the learning process. The new approach discovers new parametric activation functions which improve performance over previous activation functions by utilizing a flexible search space that can represent activation functions in an arbitrary computation graph. In this manner, the activation functions are customized to both time and space for a given neural network architecture.

An element construction unit compares output values of one or more elements included in an intermediate layer calculated by an output value calculating unit with a threshold value, and the number of elements included in the intermediate layer is maintained when any of the output values out of the output values of the one or more elements included in the intermediate layer is greater than the threshold value, and the number of elements included in the intermediate layer is increased when all of the output values of the one or more elements included in the intermediate layer are equal to or less than the threshold value.

In various examples, a representative subset of data points are queried or selected using integer programming to minimize the Wasserstein distance between the selected data points and the data set from which they were selected. A Generalized Benders Decomposition (GBD) may be used to decompose and iteratively solve the minimization problem, providing a globally optimal solution (an identified subset of data points that match the distribution of their data set) within a threshold tolerance. Data selection may be accelerated by applying one or more constraints while iterating, such as optimality cuts that leverage properties of the Wasserstein distance and/or pruning constraints that reduce the search space of candidate data points. In an active learning implementation, a representative subset of unlabeled data points may be selected using GBD, labeled, and used to train machine learning model(s) over one or more cycles of active learning.

A device for implementing a tensor-train decomposition operation for a respective convolutional layer of a convolutional neural network (CNN) is provided. The device is configured to receive input data comprising a first number of channels, and perform a 1×1 convolution on the input data to obtain a plurality of data groups. The plurality of data groups comprises a second number of channels. The device is further configured to perform a group convolution on the plurality of data groups to obtain intermediate data comprising a third number of channels, and perform a 1×1 convolution on the intermediate data to obtain output data comprising a fourth number of channels.

Methods and systems for computationally simulating an N-body physical system are disclosed. A compound object X having N elementary parts E may be decomposed into J subsystems, each including one or more of the elementary parts and having a position vector r.sub.j and state vector .sub.j. A mural network having J nodes each corresponding to one of the subsystems may be constructed, the nodes including leaf nodes, a non-leaf root node, and intermediate non-leaf nodes, each being configured to compute an activation corresponding to the state of a respective subsystem. Upon receiving input data for the parts E, each node may compute .sub.j from r.sub.j and .sub.j of its child nodes using a covariant aggregation rule representing .sub.j as a tensor that is covariant to rotations of the rotation group SO(3). A Clebsch-Gordan transform may be applied to reduce tensor products to irreducible covariant vectors, and .sub.j of the root node may be computed as output of the ANN.

The present invention is directed to systems and methods for detecting objects in a radar image stream. Embodiments of the invention can receive a data stream from radar sensors and use a deep neural network to convert the received data stream into a set of semantic labels, where each semantic label corresponds to an object in the radar data stream that the deep neural network has identified. Processing units running the deep neural network may be collocated onboard an airborne vehicle along with the radar sensor(s). The processing units can be configured with powerful, high-speed graphics processing units or field-programmable gate arrays that are low in size, weight, and power requirements. Embodiments of the invention are also directed to providing innovative advances to object recognition training systems that utilize a detector and an object recognition cascade to analyze radar image streams in real time. The object recognition cascade can comprise at least one recognizer that receives a non-background stream of image patches from a detector and automatically assigns one or more semantic labels to each non-background image patch. In some embodiments, a separate recognizer for the background analysis of patches may also be incorporated. There may be multiple detectors and multiple recognizers, depending on the design of the cascade. Embodiments of the invention also include novel methods to tailor deep neural network algorithms to successfully process radar imagery, utilizing techniques such as normalization, sampling, data augmentation, foveation, cascade architectures, and label harmonization.

An element construction unit compares output values of one or more elements included in an intermediate layer calculated by an output value calculating unit with a threshold value, and the number of elements included in the intermediate layer is maintained when any of the output values out of the output values of the one or more elements included in the intermediate layer is greater than the threshold value, and the number of elements included in the intermediate layer is increased when all of the output values of the one or more elements included in the intermediate layer are equal to or less than the threshold value.

The present invention is directed to systems and methods for detecting objects in a radar image stream. Embodiments of the invention can receive a data stream from radar sensors and use a deep neural network to convert the received data stream into a set of semantic labels, where each semantic label corresponds to an object in the radar data stream that the deep neural network has identified. Processing units running the deep neural network may be collocated onboard an airborne vehicle along with the radar sensor(s). The processing units can be configured with powerful, high-speed graphics processing units or field-programmable gate arrays that are low in size, weight, and power requirements. Embodiments of the invention are also directed to providing innovative advances to object recognition training systems that utilize a detector and an object recognition cascade to analyze radar image streams in real time. The object recognition cascade can comprise at least one recognizer that receives a non-background stream of image patches from a detector and automatically assigns one or more semantic labels to each non-background image patch. In some embodiments, a separate recognizer for the background analysis of patches may also be incorporated. There may be multiple detectors and multiple recognizers, depending on the design of the cascade. Embodiments of the invention also include novel methods to tailor deep neural network algorithms to successfully process radar imagery, utilizing techniques such as normalization, sampling, data augmentation, foveation, cascade architectures, and label harmonization.

The present invention is directed to systems and methods for detecting objects in a radar image stream. Embodiments of the invention can receive a data stream from radar sensors and use a deep neural network to convert the received data stream into a set of semantic labels, where each semantic label corresponds to an object in the radar data stream that the deep neural network has identified. Processing units running the deep neural network may be collocated onboard an airborne vehicle along with the radar sensor(s). The processing units can be configured with powerful, high-speed graphics processing units or field-programmable gate arrays that are low in size, weight, and power requirements. Embodiments of the invention are also directed to providing innovative advances to object recognition training systems that utilize a detector and an object recognition cascade to analyze radar image streams in real time. The object recognition cascade can comprise at least one recognizer that receives a non-background stream of image patches from a detector and automatically assigns one or more semantic labels to each non-background image patch. In some embodiments, a separate recognizer for the background analysis of patches may also be incorporated. There may be multiple detectors and multiple recognizers, depending on the design of the cascade. Embodiments of the invention also include novel methods to tailor deep neural network algorithms to successfully process radar imagery, utilizing techniques such as normalization, sampling, data augmentation, foveation, cascade architectures, and label harmonization.