Deep learning as an advanced concept of artificial intelligence

Trinity Journal of Management, IT & Media (TJMITM)
Year: 2018 (Jan-Dec), Volume: (9), Issue. (1)
First page: (15) Last page: (18)
Online ISSN: A/F
Print ISSN: 2320-6470
doi: 10.48165/tjmitm.2018.0903

Deep learning asan advanced concept of artificial intelligence 
Megha Gupta1 and Dr. Jitender Rai2

1Research Scholar
2Associate Professor, Tecnia Institute of Advanced Studies 

Corresponding author email id:

Received:
9 -04-2018

Accepted:
04-06-2018

Online Published:
20-07-2018

How to cite the Article

Gupta1, M., & Rai, J. (2018). Deep learning asan advanced concept of artificial intelligence. Trinity Journal of Management, IT & Media, 9(1), 15–18. https://doi.org/10.48165/tjmitm.2018.0903 Cite
Gupta1, Megha, and Jitender Rai. “Deep Learning Asan Advanced Concept of Artificial Intelligence.” Trinity Journal of Management, IT & Media, vol. 9, no. 1, 2018, pp. 15–18, http://doi.org/10.48165/tjmitm.2018.0903. Cite
1.
Gupta1 M, Rai J. Deep learning asan advanced concept of artificial intelligence. TJMITM. 2018;9(1):15‑8. DOI: 10.48165/tjmitm.2018.0903 Cite
This image has an empty alt attribute; its file name is images.png
View on Google Scholar

ABSTRACT

This paper represented on the Deep learning technique growing  in the learning community of machines, as traditional learning  architecture has proven incompetent for the machine learning  challenging tasks and strong feature of artificial intelligence (AI).  Increasing and widespread availability of computing power,  along the use of efficient training and improvement algorithms,  has made it possible to implement, until then, the concept of deep  learning. These development events deep learning architecture  and algorithms look at cognitive neuroscience and point to  biologically inspired solutions for learning. This paper  represented on the rule of Convolutional Neural Networks  (CNNs), Neural Networks (SNNs) and Hierarchical Temporary  Memory (HTM), and other related techniques to the least mature  technique. 

KEYWORDS

Neuron Model, Predictive State model, Echo Model, Spike  Neural Network