Itt Corporation

Thomas B Slack

Jeffrey N Denenberg

Chuan-Chieh Tan

Allen R Smith

A probabilistic learning element for performing task independent sequential pattern recognition. The element receives sequences of objects and outputs sequences of recognized states composed of objects. A plurality of memory elements are utilized to store received objects in sequence and for storing in context learned information including previously learned states, objects contained in previously learned states, positional information for each object in a learned state and other predetermined types of knowledge relating to previously learned states and objects contained therein. The element correlates sequences of received objects with learned information relating to previously learned states for providing conditional probabilities to possible sequences of recognized states. The most likely state sequence is determined and outputted as a recognized sequence when the element detects that a state has ended. The memory for storing learned information is a context organized memory including a plurality of tree structures having various types of information stored in nodes thereof with certain of the tree structures including at each node an attribute list referring to other tree structures whereby searching is facilitated and unnecessary searching eliminated. The element derives support coefficients relating to how much information was available when calculating conditional probabilities and support coefficients and conditional probabilities are combined to provide a rating of confidence. When the rating of confidence exceeds a predetermined level, the element is caused to store the outputted recognized state sequence as a learned state sequence with the memories storing various types of knowledge relating to the learned sequence of states.

Probabilistic learning element

A probabilistic learning element for performing task independent sequential pattern recognition employs context driven searching. The element receives sequences of objects and outputs sequences of recognized states composed of objects. The element includes a short term memory for storing received objects in sequential context and long term memories for storing in sequential context previously learned states and predetermined types of knowledge relating to the previously learned states. The element correlates the information stored in the short term memory with information stored in the long term memories for assigning probabilities to possible next states in the sequence of recognized states. The correlation is facilitated by using the context of the information stored in the short term memory as a pointer to the context of the information stored in the long term memories. Based upon the probabilities of the possible next states the most likely next state is determined and outputted as a recognized next state in the recognized state sequence when the element determines that a state has ended. The element additionally includes means for providing a rating of confidence in the recognized next state. The ratings of confidence for a sequence of recognized states are accumulated and if the accumulated value exceeds a predetermined threshold level the element will be caused to store the recognized state sequence as a learned state sequence.

Probabilistic learning element employing context drive searching

A probabilistic learning element particularly adapted for use as a task independent sequential pattern recognition device receives sequences of objects and outputs sequences of recognized states composed of objects and includes a plurality of memories for storing the received sequences of objects and previously learned states as well as predetermined types of knowledge relating to previously learned states. The sequences of received objects are correlated with the information relating to the previously learned states in order to assign probabilities to possible next states in the sequence of recognized states. Based upon the probabilities of the possible next states the most likely next state is determined and outputted as a recognized next state in the recognized state sequence when the element determines that a state has ended. The element additionally includes means for providing a rating of confidence in the recognized next state. The ratings of confidence for a sequence of recognized stated are accumulated and if the accumulated value exceeds a predetermined threshold level the element will be caused to store the recognized state sequence as a learned state sequence.

Growing community of inventors

Oxford, CT, United States of America

Thomas B Slack