a. What is pattern recognition b. Techniques for pattern recognition c. General steps in pattern recognition -input data representation: feature extraction and feature selection -training -classification and recognition d. Application areas of pattern recognition e. Pattern recognition for process monitoring and diagnosis f.Deep Learning and Pattern recognition a. What is pattern recognition -Pattern recognition involves findings patterns and similarities – to help solve complex problems – make prediction -Basis for problem solving -Filter unnecessary information -Patterns exists in TEXT, NUMBERS and IMAGES -Finding repetition and commonality -- recurrent patterns -Distinguished patterns attributes, extract features, compare patterns for a match or mismatch -can be implemented in any kind of industry because where there is data, there are similarities in the data. b. Techniques for Pattern Recognition Artificial Neural Network Statistical Techniques c. General Steps in Pattern Recognition d. Application Areas of Pattern recognition e. Pattern recognition for process monitoring and diagnosis f. Deep learning and pattern recognition
Deep learning is based on artificial neural networks with representation learning where learning can be supervised, semi-supervised or unsupervised. Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks (CNN) have been applied in computer vision, machine vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs. Researchers have reported results obtained are comparable to and in some cases surpassing human expert performance.