University System of Maryland

Daniel P Lathrop

Alessandro Restelli

Anthony Robert Mautino

Itamar Shani

Heidi Komkov

Heidi Myers

Peter Megson

Vedran Lekic

Geophysical anomalies in an area or region can be detected, characterized, or otherwise mapped using a combination of environmental and geophysical sensor data acquired using a vehicle, which may be a remotely operated or autonomously controlled unmanned vehicle. Anomalies are detected by processing the environmental sensor data and geophysical sensor data using artificial intelligence algorithms, programs, or models. As an example, the artificial intelligence algorithms, programs, or models can include machine learning algorithms, programs, or models. The environmental sensor data are processed to generate control parameters for controlling the acquisition and/or processing of the geophysical sensor data optimized for environmental conditions in the area.

Vehicle-based anomaly detection using artificial intelligence and combined environmental and geophysical sensor data

A variable sensitivity node for a neural network that can be implemented as an information processing device such as an ASIC, and can be adjusted simply by applying immediate weights or parameters that change and/or amplify or de-amplify the output of the nodes. The information processing device has one or more nodes each with an input setting channel, a logic element configured to translate the input signal into the output signal based on a mathematical function that includes a parameter setting, and a parameter-setting element configured to set the parameter setting based on a control input to the input setting channel, thereby altering the mathematical relationship of the logic element without compromising speed and efficiency.

Variable sensitivity node

An integrated circuit device for reservoir computing can include a weighted input layer, an unweighted, asynchronous, internal recurrent neural network made up of nodes having binary weighting, and a weighted output layer. Weighting of output signals can be performed using predetermined weighted sums stored in memory. Application specific integrated circuit (ASIC) embodiments may include programmable nodes. Characteristics of the reservoir of the device can be tunable to perform rapid processing and pattern recognition of signals at relatively large rates.

Integrated circuit designs for reservoir computing and machine learning

Growing community of inventors

University Park, MD, United States of America

Daniel P Lathrop