Deep learning based image recognition system with neural network architecture.

Abstract

Machine learning allows us to obtain useful information from raw data for quick and efficient solving of complex data-intensive tasks. As a sub-sector of artificial intelligence, machine learning explores study and construction of algorithms that make data-based predictions and are capable of shaping the learning process accordingly - such algorithms are far more effective than the technique of using strictly static program instructions. Machine learning algorithms are used in a wide variety of computational tasks, where it is difficult or infeasible to design and implement an explicit algorithm with decent performance. Deep learning is a branch of machine learning, based on a set of algorithms that model high-level abstractions in data by applying a depth graph with multiple processing layers, built from several linear or non-linear transformations. Research in this area is aimed at getting better representations and creating models for training on these representations from large-scale unlabeled data. Deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks and recurrent neural networks have been applied to fields including computer vision, speech recognition, natural language processing, sound recognition, and bioinformatics where they have produced cutting-edge results in a variety of cases. This article covers the concepts of machine learning, deep learning and image recognition. A specific example (with step-by-step explanation) of using deep learning for building an image recognition system with a neural network architecture is given. The resulting system provides ample opportunities to automate the technological processes and increase their efficiency. The concept of the system can be adapted to the tasks of a new type.