Ensemble learning based image classification systems

Abstract

An ensemble learning based image classification system contains multiple cellular neural networks (CNN) based integrated circuits (ICs) operatively coupling together as a set of base learners of an ensemble for an image classification task. Each CNN based IC is configured with at least one distinct deep learning model in form of filter coefficients. The ensemble learning based image classificationsystem further contains a controller configured as a meta learner of the ensemble and a memory based data buffer for holding various data used in the ensemble by the controller and the CNN based ICs.Various data may include input imagery data to be classified. Various data may also include extracted feature vectors or image classification outputs out of the set of base learners. The extracted feature vectors or image classification outputs are then used by the meta learner to further perform the image classification task.

Description

technical field [0001] This patent document relates generally to the field of machine learning. More specifically, this paper deals with ensemble learning based image classification systems. Background technique [0002] Cellular Neural Networks or Cellular Nonlinear Networks (CNNs) have been applied to many different fields and problems, including but not limited to image processing since 1988. However, most state-of-the-art CNN methods are either based on software solutions (e.g., convolutional neural networks, recurrent neural networks, etc.), or on hardware designed for other purposes (e.g., graphics processing, general computing, etc.). Consequently, CNN state-of-the-art methods are computationally too slow and / or too expensive to be practical for processing large amounts of image data. Image data may be from any two-dimensional data (eg, still photographs, pictures, frames of a video stream, converted forms of speech data, etc.). [0003] Ensemble learning is a mach...

AI Technical Summary

Problems solved by technology

Therefore, CNN state-of-the-art methods are too slow and / or too expensive in terms of computational speed, and thus impractical for processing large amounts of image data

Images