Lawrence R. Hunter
Architects at Alcott St, Denver, CO
License number
Colorado 203216
Issued Date
Dec 13, 1995
Renew Date
Jan 22, 2016
Expiration Date
Oct 31, 2017
Type
Architect
Address
Address
3453 Alcott St, Denver, CO 80211
Professional information
Architect
Position:
Owner at Hunter Design Studio
Location:
Greater Denver Area
Industry:
Architecture & Planning
Work:
Hunter Design Studio
-
Owner
Allred & Associates
2008 - 2009
-
Project Manager
Hunter Design Studio
2002 - 2008
-
Owner
Grey Wolf Studio
2000 - 2001
-
Architect
OZ Architecture
1991 - 2000
-
Architect
Education:
University of Colorado Denver
M.A., Architecture
M.A., Architecture
Machine Learning Systems And Methods
US Patent:
7389277, Jun 17, 2008
Filed:
Jul 8, 2005
Appl. No.:
11/177200
Inventors:
Hung-Han Chen - Watertown MA, US
Lawrence Hunter - Denver CO, US
Harry Towsley Poteat - Boston MA, US
Kristin Kendall Snow - Somerville MA, US
Lawrence Hunter - Denver CO, US
Harry Towsley Poteat - Boston MA, US
Kristin Kendall Snow - Somerville MA, US
Assignee:
Medical Scientists, Inc. - Irvine CA
International Classification:
G06E 1/00, G06E 3/00, G06F 15/18, G06G 7/00
US Classification:
706 21
Abstract:
A method for using machine learning to solve problems having either a “positive” result (the event occurred) or a “negative” result (the event did not occur), in which the probability of a positive result is very low and the consequences of the positive result are significant. Training data is obtained and a subset of that data is distilled for application to a machine learning system. The training data includes some records corresponding to the positive result, some nearest neighbors from the records corresponding to the negative result, and some other records corresponding to the negative result. The machine learning system uses a co-evolution approach to obtain a rule set for predicting results after a number of cycles. The machine system uses a fitness function derived for use with the type of problem, such as a fitness function based on the sensitivity and positive predictive value of the rules. The rules are validated using the entire set of training data.
Systems And Methods For Analyzing Data To Predict Medical Outcomes
US Patent:
2008012, May 22, 2008
Filed:
Jan 24, 2008
Appl. No.:
12/019405
Inventors:
Hung-Han Chen - Watertown MA, US
Lawrence Hunter - Denver CO, US
Harry Poteat - Boston MA, US
Kristin Snow - Somerville MA, US
Lawrence Hunter - Denver CO, US
Harry Poteat - Boston MA, US
Kristin Snow - Somerville MA, US
Assignee:
MEDICAL SCIENTISTS, INC. - Irvine CA
International Classification:
G06N 5/04
US Classification:
706061000
Abstract:
A method for using machine learning to solve problems having either a “positive” result (the event occurred) or a “negative” result (the event did not occur), in which the probability of a positive result is very low and the consequences of the positive result are significant. Training data is obtained and a subset of that data is distilled for application to a machine learning system. The training data includes some records corresponding to the positive result, some nearest neighbors from the records corresponding to the negative result, and some other records corresponding to the negative result. The machine learning system uses a co-evolution approach to obtain a rule set for predicting results after a number of cycles. The machine system uses a fitness function derived for use with the type of problem, such as a fitness function based on the sensitivity and positive predictive value of the rules. The rules are validated using the entire set of training data.
Machine Learning Method
US Patent:
6917926, Jul 12, 2005
Filed:
Jun 15, 2001
Appl. No.:
09/882502
Inventors:
Hung-Han Chen - Watertown MA, US
Lawrence Hunter - Denver CO, US
Harry Towsley Poteat - Boston MA, US
Kristin Kendall Snow - Somerville MA, US
Lawrence Hunter - Denver CO, US
Harry Towsley Poteat - Boston MA, US
Kristin Kendall Snow - Somerville MA, US
Assignee:
Medical Scientists, Inc. - Irvine CA
International Classification:
G06F015/18
US Classification:
706 12
Abstract:
A method for using machine learning to solve problems having either a “positive” result (the event occurred) or a “negative” result (the event did not occur), in which the probability of a positive result is very low and the consequences of the positive result are significant. Training data is obtained and a subset of that data is distilled for application to a machine learning system. The training data includes some records corresponding to the positive result, some nearest neighbors from the records corresponding to the negative result, and some other records corresponding to the negative result. The machine learning system uses a co-evolution approach to obtain a rule set for predicting results after a number of cycles. The machine system uses a fitness function derived for use with the type of problem, such as a fitness function based on the sensitivity and positive predictive value of the rules. The rules are validated using the entire set of training data.
Lawrence Hunter
Location:
Denver, Colorado
Industry:
Research