Abstract: The present invention is directed to a system and methods of predicting protein function through a process of encoding protein structural information into a computer readable format and the use of a convolutional neural network designed to recognize such encoded format.

Abstract: Embodiments of the present invention provide a system and method to automatically screen images from a plurality of fundus cameras for a plurality of retinal diseases. The system comprises stacked autoencoders, amplitude modulation-frequency modulation filters, and artificial neural networks. An embodiment of the present invention uses a multi-class classifier, such as a support vector machine (multi-class SVM) classifier, to determine a plurality of retinal pathologies. An exemplary embodiment of the present invention is validated on a proprietary database of thousands of images (for example over 250,000 retinal images) from multiple cameras, ranging from the table-top fundus cameras to portable hand-held cameras.

Abstract: Apparatus and methods control predistortion of an RF transmitter. A base station or a mobile station can utilize predistortion to improve linearity characteristics of the RF power amplifier. When used effectively, predistortion limits spectral growth such that the amplified signal complies with regulatory requirements. With respect to bursty signals, specific improvement techniques are disclosed. A first technique is related to adaptation using only a smaller subset of samples of a burst. A second technique is related to selective application of digital predistortion, such as, only under high power conditions for a power amplifier. A third technique is directed to adaptation of less than all of the coefficients. These improvements permit the use of a smaller and less expensive amplifier for a given power class and can lengthen battery life for a mobile unit.