The present disclosure provides a leakage measurement error compensation method based on cloud-edge collaborative computing, implemented on a communication network formed by interconnection between a leakage current edge monitoring terminal and a power consumption management cloud platform, and including the following steps: monitoring, by the leakage current edge monitoring terminal, leakage current data, and sending the leakage current data to the power consumption management cloud platform; iteratively training, by the power consumption management cloud platform, a pseudo-leakage compensation model by using the received leakage current data, continuously updating pseudo-leakage model parameters, and feeding the pseudo-leakage model parameters back to the leakage current edge monitoring terminal; and processing, by the leakage current edge monitoring terminal, the leakage current data according to the pseudo-leakage compensation model parameters, so as to eliminate the influence of a pseudo-leakage phenomenon in the leakage current data.

A processor system comprises two groups of registers and a hardware channel convolution processor unit. The first group of registers is configured to store data elements of channels of a portion of a convolution data matrix. Each register stores at least one data element from each channel. The second group of registers is configured to store data elements of convolution weight matrices including a separate matrix for each channel. Each register stores at least one data element from each matrix. The hardware channel convolution processor unit is configured to multiply each data element in a first and second portion of the first group of registers with a corresponding data element in the second group of registers to determine corresponding multiplication results and sum together the multiplication results for each specific channel to determine two corresponding channel convolution result data elements in a corresponding channel convolution result matrix.

Various embodiments include a method for producing a quality test system executing a quality test model with a filter mask and a quality model to determine a quality feature of a battery cell. The system has an electrochemical impedance spectroscopic unit for capturing test data relating to the battery within a frequency range. The method includes: creating the model; and producing the system. Creating the model includes: capturing spectroscopic learning data; creating the filter mask using a first machine learning method with analysis data from part of the frequency range by consulting the filter mask and creating the model using a second machine learning method. The first and the second learning method are coupled based on the learning data. The first machine learning method creates a filter mask determining the analysis data such that the second machine learning method creates a quality model optimized with respect to maximizing the quality.

The present invention relates to a method, a computer program, and an apparatus for training a neural network for semantic image segmentation. The invention further relates to an in-car control unit or a backend system, which make use of such a method or apparatus, and to a vehicle comprising such an in-car control unit. In some embodiments and in a first step, image data of a sequence of image frames are received. Then a frame-based evaluation of semantic segmentation predictions of one or more objects in individual image frames is performed. Furthermore, a sequence-based evaluation of temporal characteristics of semantic segmentation predictions of said one or more objects in at least two image frames is performed. The results of the frame-based evaluation and the sequence-based evaluation are combined.

A system and method are described, for automatically analyzing and understanding individual and group activities and interactions. The method includes receiving at least one image from a video of a scene showing one or more individual objects or humans at a given time; applying at least one machine learning or artificial intelligence technique to automatically learn a spatial, temporal or a spatio-temporal informative representation of the image and video content for activity recognition; and identifying and analyzing individual and group activities in the scene.

Presented are systems and methods for automatically creating and labeling training data for training-based radio, comprising receiving, at a receiver, a frame that comprises a modulated radio frequency (RF) signal comprising a set of waveforms that correspond to payload data. The payload data comprises a sequence of random bits. In embodiments, until a stopping condition is met one or more steps are performed, comprising detecting the frame; demodulating the modulated RF signal to reconstruct the sequence of random bits; using the reconstructed sequence to determine whether the payload data has been correctly received; in response to determining that the payload data has not been correctly received, discarding it and, otherwise, accepting the sequence of random bits as a training label; associating the training label with the modulated RF signal to generate labeled training data; and appending the labeled training data to a labeled training data set.

An information processing apparatus according to an embodiment includes one or more hardware processors. The hardware processors obtain a first categorical distribution sequence corresponding to first input data and obtain a second categorical distribution sequence corresponding to second input data neighboring the first input data, by using a prediction model outputting a categorical distribution sequence representing a sequence of L categorical distributions for a single input data piece, where, L is a natural number of two or more. The hardware processors calculate, for each i of 1 to L, an inter-distribution distance between i-th categorical distributions in the first and second categorical distribution sequences. The hardware processors calculate a sum of L inter-distribution distances. The hardware processors update the prediction model's parameters to lessen the sum.

A novel interpretable and steerable deep sequence modeling technique is disclosed. The technique combines prototype learning and RNNs to achieve both interpretability and high accuracy. Experiments and case studies on different real-world sequence prediction/classification tasks demonstrate that the model is not only as accurate as other state-of-the-art machine learning techniques but also much more interpretable. In addition, a large-scale user study on Amazon Mechanical Turk demonstrates that for familiar domains like sentiment analysis on texts, the model is able to select high quality prototypes that are well aligned with human knowledge for prediction and interpretation. Furthermore, the model obtains better interpretability without a loss of performance by incorporating the feedback from a user study to update the prototypes, demonstrating the benefits of involving human-in-the-loop for interpretable machine learning.

A keypoint detection system includes: a camera system including at least one camera; and a processor and memory, the processor and memory being configured to: receive an image captured by the camera system; compute a plurality of keypoints in the image using a convolutional neural network including: a first layer implementing a first convolutional kernel; a second layer implementing a second convolutional kernel; an output layer; and a plurality of connections between the first layer and the second layer and between the second layer and the output layer, each of the connections having a corresponding weight stored in the memory; and output the plurality of keypoints of the image computed by the convolutional neural network.

System and techniques for vehicle environment modeling with a camera are described herein. A device for modeling an environment comprises: a hardware sensor interface to obtain a sequence of unrectified images representative of a road environment, the sequence of unrectified images including a first unrectified image, a previous unrectified image, and a previous-previous unrectified image; and processing circuitry to: provide the first unrectified image, the previous unrectified image, and the previous-previous unrectified image to an artificial neural network (ANN) to produce a three-dimensional structure of a scene; determine a selected homography; and apply the selected homography to the three-dimensional structure of the scene to create a model of the road environment.