International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Deep Learning AI: is Changing over Technology World; What, How, Why?

Author : Rashmi Mothkur ¹ Poornima K M ²

Date of Publication :7th July 2016

Abstract: Artifiicial Intelligence technology is increasingly prevalent in our everyday lives. It is spread beyond the academic world with major players like Google, Microsoft and Face book. This resurgence has been powered in no small part by a new trend in Artificial Intelligence, specifically in machine learning known as Deep Learning. Deep learning is an approach and an attitude to learning, where the learner uses higher-order cognitive skills such as the ability to analyse, synthesize, solve problems and thinks meta cognitively in order to construct long-term understanding. It involves the critical analysis of new ideas, linking them to already known concepts and principles so that this understanding can be used for problem solving in new, unfamiliar contexts. Deep learning entails a sustained, substantial and positive influence on the way students act, think or feel. Deep learning promotes understanding and application for life. Deep learners reflect on the personal significance of what they are learning. They are autonomous –they virtually teach themselves. But they are also collaborative learners, with high meta-cognitive and learning skills. Deep Learning is going to teach us all the lesson of our lives: Jobs Are for Machines. This paper gives an overview of need for Deep Learning, Architecture, frameworks, applications and future scope of deep learning.

Reference :

1. R.Rojas,“chapter7-neural networks: a systematic introduction”, springer, 1996
2. david h ackley, geofrey e hinton, “a learning algorithm for boltzmann machines”, cognitive science, vol:9, pp:147- 169,1985.
3. samir roy, udit chakraborthy, “introduction to soft computing: neuro fuzzy and genetic algorithms”,pearson, 2013.
4. winfred philips, “chapter 2-computers and intelligence”, consortium on cognitive science instruction.
5. yaniv taigman, ming yang, marcâ€Ÿaurelio ranzato, “deepface: closing the gap to human-level performance in face verification”, ieee conference on computer vision and pattern recognition, pp: 1701-1708, 2014.
6. li deng, “three classes of deep learning architectures and their applications: a tutorial survey”, transactions on signal and information processing, 2011.
7. pascal vincent, hugo larochelle, “stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion” journal of machine learning research, pp: 3371-3408, 2010
8. yang qing jia , evan shelhamer , jeff donahue, sergey karayev, “caffe: convolutional architecture for fast feature embedding”, 22nd international conference on multimedia,pp:675-678,acm,2014.
9. "the last ai breakthrough deepmind made before google bought it",the physicsar arxivblog,retrieved 12 october 2014
10. best of 2014: google's secretive deepmind startup unveils a "neural turing machine", mit technology review.
11. hay,timothy,“siri inc. launches 'do engine'application for iphone", retrieved 9 october 2011.
12. yusuke sugumori, “practical applications of deep learning”, packt publishers, may 2016.
13. http://www.wordstream.com/blog/ws/2016/02/29/google - adwords-industry-benchmarks.
14. http://luajit.org/luajit.html.
15. tom simonite,"facebook creates software that matches faces almost as well as you do", massachusetts institute of technology review, march 17, 2014