A Survey on Supervised Convolutional Neural Network and Its Major Applications

A Survey on Supervised Convolutional Neural Network and Its Major Applications

D. T. Mane, U. V. Kulkarni
DOI: 10.4018/978-1-7998-0414-7.ch059
(Individual Chapters)
No Current Special Offers


With the advances in the computer science field, various new data science techniques have been emerged. Convolutional Neural Network (CNN) is one of the Deep Learning techniques which have captured lots of attention as far as real world applications are considered. It is nothing but the multilayer architecture with hidden computational power which detects features itself. It doesn't require any handcrafted features. The remarkable increase in the computational power of Convolutional Neural Network is due to the use of Graphics processor units, parallel computing, also the availability of large amount of data in various variety forms. This paper gives the broad view of various supervised Convolutional Neural Network applications with its salient features in the fields, mainly Computer vision for Pattern and Object Detection, Natural Language Processing, Speech Recognition, Medical image analysis.
Chapter Preview

2. History Of Cnn

The idea of modeling brain networks has been a research question even before the advent of computers. In initial stages, neural networks were evaluated with propositional logic. Then with the discovery of concepts such as convolution and back propagation applied to neural networks, NN got better. Until the emergence of GPUs, the computers were not fast enough to implement multi-layer neural networks. So NN were not commercially viable. With the power of GPUs and more efficient algorithms, CNNs can be applied to real life applications (see Table 1).

Table 1.
Time line chart of CNN
1940 - 1979Emergence of NN1943McCulloch, Pitts compare neural activity with propositional logic.
1949Hebb proposes cell assembly theory.
1962Hubel and Wiesel model the visual system in Cat brain.
1980 - 1998Concept of Convolution1980Fukushima proposed a self-learning NN which preserves the intrinsic geometric representation.
1989LeCun et al demonstrated the use of back propagated CNN for real life Application.
1999-2010More Efficient CNN1999Poggio et al proposed max pooling.
2006Ranzato et al proposed max pooling for CNN.
2011-PresentGPGPU acceleration of CNN2011Ciresan et al put forth the concept of CNN on GPUs.
2012Hinton et al demonstrated Drop Out for CNN.
2013Lecun et al proposed Drop Connect for better CNN.
2014Min Lin et al designed Network in Network concept for CNN.
2015Google releases different open source libraries for CNN

Complete Chapter List

Search this Book: