Information Systems Laboratories, Inc.

Brian Watson

Joseph R Guerci

Jameson Bergin

David R Kirk

Jeffrey Richard Ridgway

Sandeep Gogineni

Gavin McGee

Joel R Studer

Colton Smith

Raymond M Guerci

A novel system and method are described that allows for implementation of compact and efficient deep learning AI solutions to advanced sensor signal processing functions. The process includes the following stages: (1) A method for generating requisite annotated training data in sufficient quantity to ensure convergence of a deep learning neural network (DNN); (2) A method for implementing the resulting DNN onto a Spiking Neural Network (SNN) architecture amenable to efficient neuromorphic integrated circuit (IC) architectures; (3) A method for implementing the solution onto a neuromorphic IC; and (4) A statistical method for ensuring reliable performance.

Process and method for real-time sensor neuromorphic processing

A system for visually tracking the trajectory of an in-flight golf ball through an x-y-z space above a driving range includes a plurality of cameras for respectively creating a video stream of the x-y-z space. Each video stream is presented on a dedicated camera focal plane with information on respective azimuth angles &#x3b8; and elevation angles &#x3d5; from the particular camera to the in-flight golf ball. A central computer is connected with the camera focal plane of each camera to identify a start point for the golf ball, to track its trajectory in the x-y-z space, and to filter out background clutter. A visual display is provided to show the in-flight golf ball from its start point to a target point in real time.

System and method for 3D optical tracking of multiple in-flight golf balls

A system for converting an analog signal into a digital data stream includes a recurrent network with a plurality of converter circuits that individually receive the same analog signal as input. The circuits then generate a plurality of spike outputs that exhibit characteristics of the analog signal. Interconnecting feedback loops from each circuit output to the input of neighboring circuits queues the plurality of spike outputs to thereby self-organize the network. A digital clock is then used to establish predetermined time intervals for counting the spike outputs to create the digital data stream.

Analog to digital conversion using recurrent neural networks

Growing community of inventors

Gainesville, FL, United States of America

Brian Watson