Michael L Commons

US Patent:

7613663, Nov 3, 2009

Filed:

Dec 18, 2006

Appl. No.:

11/612268

Inventors:

Michael Lamport Commons - Cambridge MA, US
Mitzi Sturgeon White - Watertown MA, US

International Classification:

G06E 1/00
G06E 3/00

US Classification:

706 15, 700 28, 600545

Abstract:

An intelligent control system based on an explicit model of cognitive development (Table 1) performs high-level functions. It comprises up to O hierarchically stacked neural networks, N,. . . , N, where m denotes the stage/order tasks performed in the first neural network, N, and O denotes the highest stage/order tasks performed in the highest-level neural network. The type of processing actions performed in a network, N, corresponds to the complexity for stage/order m. Thus Nperforms tasks at the level corresponding to stage/order 1. Nprocesses information at the level corresponding to stage/order 5. Stacked neural networks begin and end at any stage/order, but information must be processed by each stage in ascending order sequence. Stages/orders cannot be skipped. Each neural network in a stack may use different architectures, interconnections, algorithms, and training methods, depending on the stage/order of the neural network and the type of intelligent control system implemented.

US Patent:

7152051, Dec 19, 2006

Filed:

Sep 30, 2002

Appl. No.:

10/261560

Inventors:

Michael Lamport Commons - Cambridge MA, US
Mitzi Sturgeon White - Watertown MA, US

International Classification:

G06F 15/18

US Classification:

706 16, 706 20

Abstract:

An intelligent control system based on an explicit model of cognitive development (Table 1) performs high-level functions. It comprises up to O hierarchically stacked neural networks, N,. . . , N, where m denotes the stage/order tasks performed in the first neural network, N, and O denotes the highest stage/order tasks performed in the highest-level neural network. The type of processing actions performed in a network, N, corresponds to the complexity for stage/order m. Thus Nperforms tasks at the level corresponding to stage/order 1. Nprocesses information at the level corresponding to stage/order 5. Stacked neural networks begin and end at any stage/order, but information must be processed by each stage in ascending order sequence. Stages/orders cannot be skipped. Each neural network in a stack may use different architectures, interconnections, algorithms, and training methods, depending on the stage/order of the neural network and the type of intelligent control system implemented.