Bernard Widrow, Juan Carlos Aragon, Brian Mitchell Percival: Cognitive memory and auto-associative neural network based search engine for computer and network located images and photographs. February 19, 2008: US07333963 (59 worldwide citation)

Designs for cognitive memory systems storing input data, images, or patterns, and retrieving it without knowledge of where stored when cognitive memory is prompted by query pattern that is related to sought stored pattern. Retrieval system of cognitive memory uses autoassociative neural networks and ...

Eric J Horvitz, Carl M Kadie: Multi-attribute specification of preferences about people, priorities and privacy for guiding messaging and communications. Microsoft Corporation, Amin & Turocy, June 27, 2006: US07069259 (49 worldwide citation)

The present invention relates to a system and methodology to facilitate multiattribute adjustments and control associated with messages and other communications and informational items that are directed to a user via automated systems. An interface, specification language, and controls are provided ...

David E Joslin, David P Clements: Cost-optimizing allocation system and method. The State of Oregon acting by and through the State Board of Higher Education on Behalf of the University of Oregon, Fenwick & West, August 7, 2001: US06272483 (45 worldwide citation)

A system for determining schedules and processing other optimization problems includes a local optimization engine and a global optimization engine. The local optimization engine operates based on heuristics, and includes a prioritizer, a constructor, and an analyzer to make large “coherent” moves i ...

Filip Ponulak, Oleg Sinyavskiy: Apparatus and methods for state-dependent learning in spiking neuron networks. Brain Corporation, Pillsbury Winthrop Shaw Pittman, March 24, 2015: US08990133 (43 worldwide citation)

State-dependent supervised learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on a connection state term and a neuron state term. Connection states may be updated based on inputs and outputs to and/o ...

Shumeet Baluja, Michele Covell: Approximate hashing functions for finding similar content. Google, Fish & Richardson P C, November 9, 2010: US07831531 (41 worldwide citation)

A method including training a plurality of learning systems, each learning system implementing a learning function and having an input and producing an output, initializing one or more data structures, and evaluating a target sample is described. Also described are methods that include initializing ...

Stephen Barnhill, Isabelle Guyon, Jason Weston: Feature selection method using support vector machine classifier. Health Discovery Corporation, Procopio Cory Hargreaves & Savitch, June 2, 2009: US07542959 (40 worldwide citation)

Identification of a determinative subset of features from within a large set of features is performed by training a support vector machine to rank the features according to classifier weights, where features are removed to determine how their removal affects the value of the classifier weights. The ...

Vikas Sindhwani, Sathiya Keerthi Selvaraj: Large scale semi-supervised linear support vector machines. Yahoo, Seth H Ostrow, Ostrow Kaufman & Frankl, July 14, 2009: US07562060 (39 worldwide citation)

A computerized system and method for large scale semi-supervised learning is provided. The training set comprises a mix of labeled and unlabeled examples. Linear classifiers based on support vector machine principles are built using these examples. One embodiment uses a fast design of a linear trans ...

Eric Bonabeau, Carl Anderson, Belinda Orme, Pablo Funes, Oliver Bandte, Mark Sullivan, Sergey Malinchik, Joseph Rothermich: Methods and systems for interactive evolutionary computing (IEC). Icosystem Corporation, Stephen B Deutsch, Foley Hoag, May 9, 2006: US07043463 (35 worldwide citation)

A method for interactive evolutionary computing may include generating a solution set based on an evolutionary scheme in which an objective function is a priori mathematically unexpressed, presenting data based on the solution set to one or more users, receiving at least one input from the user(s), ...

Oleg Sinyavskiy, Vadim Polonichko: Dynamically reconfigurable stochastic learning apparatus and methods. Brain Corporation, Pillsbury Winthrop Shaw Pittman, April 21, 2015: US09015092 (29 worldwide citation)

Generalized learning rules may be implemented. A framework may be used to enable adaptive signal processing system to flexibly combine different learning rules (supervised, unsupervised, reinforcement learning) with different methods (online or batch learning). The generalized learning framework may ...

Taher Haveliwala, Benedict Gomes, Amitabh K Singhal: Using game responses to gather data. Google, Harrity & Harrity, October 4, 2011: US08032483 (29 worldwide citation)

A system provides images or questions to multiple game participants and receives labels or answers in response thereto. The system uses the labels or answers for various data gathering purposes.