Data Analytics: Role of Activation Function in Neural Net
K. Dhana Sree
K.Dhana Sree, Department of CSE, Vardhaman College of Engineering, Hyderabad (Telangana), India
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 299-302 | Volume-8 Issue-5, March 2019 | Retrieval Number: E3303038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Most of the data science contemporary fields like Artificial Intelligence, Machine Learning and Deep Learning are taking advantage of a common model- The Neural Network. Neural network which can learn from experience are becoming popular in solving many of real worlds NP-hard problems. Today any prediction application is taking the support of Neural Network. The accuracy of the neural network models depends on major of the design components like the hidden layers and the activation functions. As we know human brain receives both relevant and irrelevant information at a time and has the capability of segregating both, where the irrelevant can be referred as noise. Just like the human brain the neurons uses activation function to separate the noise from the input and reduce the error. This paper presents the role of hidden layers and activation functions in measuring the accuracy of the Neural Network.
Keyword: Artificial Intelligence, Machine Learning, Neural Networks, Activation function, Neurons.
Scope of the Article: Big Data Analytics