Publication Date:
2019-08-28
Description:
A network learning translation invariance algorithm to compute interpolation functions is presented. This algorithm with one fixed receptive field can construct a linear transformation compensating for gain changes, sensor position jitter, and sensor loss when there are enough remaining sensors to adequately sample the input images. However, when the images are undersampled and complete compensation is not possible, the algorithm need to be modified. For moderate sensor losses, the algorithm works if the transformation weight adjustment is restricted to the weights to output units affected by the loss.
Keywords:
CYBERNETICS
Type:
In: Human vision, visual processing, and digital display II; Proceedings of the Meeting, San Jose, CA, Feb. 27-Mar. 1, 1991 (A93-25363 08-54); p. 134-146.
Format:
text
Permalink