A method is disclosed. The method models a plurality of visual cortex neurons, models one or more connections between at least two visual cortex neurons in the plurality of visual cortex neurons, assigns synaptic weight value to at least one of the one or more connections, simulates application of one or more electrical signals to at least one visual cortex neuron in the plurality of visual cortex neurons, adjusts the synaptic weight value assigned to at least one of the one or more connection based on the one or more electrical signals, and generates an orientation map of the plurality of visual cortex neurons based on the adjusted synaptic weight values.

This disclosure relates to an apparatus for object detection. The apparatus comprises a video camera, an object detector, and a controller. The video camera may be configured to generate a video stream of frames. The object detector may be configured to accept the video stream as input data and to perform object detection. The controller may be coupled to the video camera and the object detector. The controller may be configured to manage object detection in order to satisfy a performance metric and/or operate within an operational constraint.

A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a baseline image and a test image; determining, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image; based on at least determining the first similarity, determining, for the test image, a first activation map for at least one CNN layer; based on at least determining the first similarity, determining, for the test image, a first gradient map for the at least one CNN layer; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map. Some examples further determine a region of interest (ROI) in the first saliency map, cropping the test image to an area corresponding to the ROI, and determine a refined similarity score.

One embodiment of the present invention sets forth a technique for evaluating labeled data. The technique includes selecting, from a set of labels for a data sample, a subset of the labels representing non-outliers in a distribution of values in the set of labels. The technique also includes aggregating the subset of the labels into a benchmark for the data sample. The technique further includes generating, based on a comparison between the benchmark and an additional label, a benchmark score associated with the data sample, and generating a set of performance metrics for labeling the data sample based on the benchmark score.

System for data collection and monitoring in an industrial environment are disclosed. A data acquisition circuit may interpret a plurality of detection values, each of the plurality of detection values corresponding to at least one of a plurality of input sensors. A data storage circuit may store sensor specifications, anticipated state information and detected values for use by a signal evaluation to determine a sensor overload status, a sensor fault status or a sensor validity value of at least one sensor in response to the plurality of detection values and at least one of an anticipated state information or a sensor specification. A response circuit may perform an operation in response to one of a sensor overload status, a sensor health status, or a sensor validity status.

Systems, methods and apparatus for network sensitive data collection are disclosed. A system according to one embodiment can include a plurality of input sensors operatively coupled to a component of an industrial environment and a data collector having a controller. The controller may include: a transmission environment circuit to determine a transmission condition corresponding to transmission of a subset of output data, a network management circuit to update a sensor data transmission protocol, a data collection band circuit to determine at least one collection parameter, a machine learning data analysis circuit to receive output data and learn at least one output data pattern, and a response circuit to adjust an operating parameter of the component based on one of a mismatch or a match of the at least one output data pattern and the state of the component.

Monitoring, systems and methods for data collection in an industrial environment are disclosed. A system may include a data collector communicatively coupled to a plurality of input channels and to a network infrastructure, wherein the data collector collects data based on a selected data collection routine, a data storage structured to store a plurality of collector routes and collected data, a data acquisition circuit structured to interpret a plurality of detection values from the collected data, and a data analysis circuit structured to analyze the collected data, and sense a change in operation and determine an aggregate rate of data being collected from the plurality of input channels. If the aggregate rate exceeds a throughput parameter the data analysis circuit alters the data collection to reduce the amount of data collected or, based on the sensed change, modify a collector route.

Aspects of the disclosure relate to determining a sign type of an unfamiliar sign. The system may include one or more processors. The one or more processors may be configured to receive an image and identify image data corresponding to a traffic sign in the image. The image data corresponding to the traffic sign may be input in a sign type model. The processors may determine that the sign type model was unable to identify a type of the traffic sign and determine one or more attributes of the traffic sign. The one or more attributes of the traffic sign may be compared to known attributes of other traffic signs and based on this comparison, a sign type of the traffic sign may be determined. The vehicle may be controlled in an autonomous driving mode based on the sign type of the traffic sign.

Systems and methods for data collection in an industrial environment are disclosed. An expert graphical user interface showing representations of components of an industrial machine to which sensors are attach is disclosed. The user interface may enable a user to select at least one of the components resulting in a search of a database of industrial machine failure modes for modes that correspond to the selected component. The corresponding failure mode may be presented to the user. The selection of the component may cause a controller to reference and implement a data collection template for configuring the system to automatically collect data from sensors associated with the selected component to detect at least one of the corresponding failure modes.

Systems and methods for monitoring a vehicle steering system are disclosed. An example monitoring system for a vehicle steering system may include a vehicle steering system comprising a rack, a pinion, and a steering column; a data acquisition circuit structured to interpret a plurality of detection values corresponding input sensors operationally coupled to the rack, the pinion, or the steering column; a data storage circuit structured to store specifications, and to buffer the plurality of detection values for a predetermined length of time. The example system may further include a timer circuit structured to generate a timing signal based on a first detected value of the plurality of detection values; a steering system analysis circuit to determine a steering system performance parameter in response to a relative phase difference and a response circuit structured to perform at least one operation in response to the steering system performance parameter.