Method and apparatus for training a neural network to learn hierarchical representations of objects and to detect and classify objects with uncertain training data
First Claim
1. A method for growing a pattern tree having a root and at least one child, said method comprising the steps of:
- (a) training the root of the pattern tree;
(b) training the children of the pattern tree; and
(c) creating at least one integration network, where said integration network receives its input from at least one of the children and root.
4 Assignments
0 Petitions
Accused Products
Abstract
A signal processing apparatus and concomitant method for learning and integrating features from multiple resolutions for detecting and/or classifying objects are presented. Neural networks in a pattern tree structure with tree-structured descriptions of objects in terms of simple sub-patterns, are grown and trained to detect and integrate the sub-patterns. A plurality of objective functions and their approximations are presented to train the neural networks to detect sub-patterns of features of some class of objects. Objective functions for training neural networks to detect objects whose positions in the training data are uncertain and for addressing supervised learning where there are potential errors in the training data are also presented.
-
Citations
19 Claims
-
1. A method for growing a pattern tree having a root and at least one child, said method comprising the steps of:
-
(a) training the root of the pattern tree; (b) training the children of the pattern tree; and (c) creating at least one integration network, where said integration network receives its input from at least one of the children and root. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A pattern tree architecture of neural networks comprising:
-
a root feature network; at least one child feature network coupled to said root feature network; and at least one integration network, where said integration network receives its input from at least one of said children and root feature networks. - View Dependent Claims (7)
-
-
8. A method for training a neural network to discover features, said method comprising the step of:
-
(a) providing the neural network with a plurality of training data; and (b) training the neural network using a function;
##EQU33## , where EFD is an error function, where y(x) is an output of a position x, N is a total number of pixels, no is a number of pixels inside of an object, u is an integration variable and Xpos is a set of all positive positions. - View Dependent Claims (9, 10)
-
-
11. A method for training a neural network to detect objects with imprecise positions, said method comprising the step of:
-
(a) providing the neural network with a plurality of training data; and (b) training the neural network using a function;
##EQU37## , where EDL is an error function, y(x) is an output of a position x, positives are positive regions and negatives are negative regions.
-
-
12. A method for training a neural network, said method comprising the step of:
-
(a) providing the neural network with a plurality of the training data; and (b) training the neural network using a function that accounts for errors in said training data, wherein said function is;
##EQU38##
-
-
13. A method for training a neural network, said method comprising the step of:
- (a) providing the neural network with a plurality of the training data; and
(b) training the neural network using a function that accounts for errors in said training data, wherein said function is;
##EQU39##
- (a) providing the neural network with a plurality of the training data; and
-
14. A method for addressing a neural network trained with training data that contains error, said method comprising the step of:
- (a) providing the neural network with a plurality of the training data that contains error; and
(b) correcting an output of the neural network using a corrected probability. - View Dependent Claims (15, 16)
- (a) providing the neural network with a plurality of the training data that contains error; and
-
17. A method for generating an integrated feature pyramid, said method comprising the steps of:
-
(a) generating a pyramid having a plurality of scales for each sample of an input signal; (b) applying oriented filtering to each of said plurality of scales of said pyramid to produce a plurality of oriented output signals; (c) squaring each of said plurality of oriented output signals to produce a squared output signal; and (d) generating a pyramid having a plurality of scales for each of said squared output signal. - View Dependent Claims (18, 19)
-
Specification