Open AccessTRANSFER LEARNING ON DEEP NEURAL NETWORK: A CASE STUDY ON FOOD-101 FOOD CLASSIFIER
Author(s) -
Prakhar Tripathi
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v05i09.037
Subject(s) - artificial intelligence , transfer of learning , computer science , deep learning , machine learning , big data , artificial neural network , flexibility (engineering) , classifier (uml) , hierarchy , deep neural networks , learning classifier system , data mining , statistics , mathematics , economics , market economy
—In the era of the ‘Big-Data’ we hear a lotabout machine learning for working on this big data.Machine learning helps us to predict and analyze datawith better accuracy and least human intervention.Machine learning is autonomous but susceptible toerrors. This is due to biased prediction when previouslytrained on small data. This leads to chain of errors thatcan`t be determined easily for long period of time. Andwhen recognized takes lot time to recognize source.There comes the idea of deep learning which achievesthe flexibility by using use nested hierarchy of concept todefine the world. But deep learning has setback of takingvery long time to train data which could be reduced byusing transfer learning.