University of California

Khalid Youssef

Louis S Bouchard

At least some embodiments of the present disclosure relate to a method of training an artificial neural network (ANN) for an artificial intelligence recognition. The method includes producing, by an ANN, outputs by feeding inputs of a training data set to the ANN; determining errors of the generated outputs from target outputs of the training data set; generating a first-order derivative matrix including first-order derivatives of the errors and a second-order derivative matrix including second-order derivatives of the errors; obtaining an approximation of the first-order derivative matrix or an approximation of the second-order derivative matrix by compressing the first-order derivative matrix or the second-order derivative matrix; and updating weights of the ANN based on the approximation of the first-order derivative matrix or the approximation of the second-order derivative matrix.

Training artificial neural networks with reduced computational complexity

A noise removal method includes receiving in a de-noising system multiple noisy copies of a target image; providing the noisy copies as input data to the de-noising system in a training phase, and determine a noise distribution for the plurality of noisy copies. The method further includes, for n stages of the de-noising system, transforming the input data into an output; reconstructing the output; and providing the reconstructed output as input data. The method may further include receiving a new image and generating a de-noised image based on the determined noise distribution.

Growing community of inventors

Los Angeles, CA, United States of America

Khalid Youssef