Loading patent…
AssigneeDDAIM Inc.
InventorsThomas J. Saleh, Laura C. Trumbull, Lawrence C. Rafsky
Estimating the term…
An electronic circuit system implementing and executing machine learning inference engines. While ML inference engines are based on (architectures and parameters defined by) configured, trained and tuned machine learning models, our design has the novel ability to support data driven, on-the-fly-reconfigured model runs. Reconfiguration and tuning operations include dynamic computational graph modifications, define-by-run alterations, changes to network depth (number of layers) and width (neurons per layer), and adjustments to weights, biases, plus activation function parameters. Neural networks supported include Feed-Forward, RNN, CNN, and Hopfield architectures, plus Ensemble, Federated, Cooperating, Adversarial, and Swarm collections. Decision Trees and Forests are also supported, as are more esoteric approaches such as ART and KAN. Our invention is capable of running both standalone and cooperatively, the cooperative processing being local and/or remote/cloud based, interfacing with telemetry applications to feed data, and machine learning software to feed new or updated models.
A digital circuit implementing a machine learning model inference engine for one or more models, wherein the machine learning model inference engine takes, as inputs, a set of measurements of an external system as delivered to the digital circuit by the external system, and produces, as an output, a final answer prediction of one-or-more attribute of the external system based on the inputs by applying one-or-more machine learning neural networks, the digital circuit comprising:
Dependencies are inferred from the claim text.