An Effective Integration of Domain Knowledge into Deep Neural Networks
ArunimaS1, KiruthikaS2, M.AswinRaj3, K.KavinKumar4, S.SuryaPrakash5
1ArunimaS, Pursuing Bachelor’s Degree, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
2KiruthikaS, Assistant Professor, Department of Computer at Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
3M.AswinRaj, Pursuing Bachelor’s Degree,. Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
4K.KavinKumar, Pursuing Bachelor’s Degree,. Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
5S.SuryaPrakash, Pursuing Bachelor’s Degree,. Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on April 01, 2020. | Manuscript published on April 10, 2020. | PP: 507-509 | Volume-9 Issue-6, April 2020. | Retrieval Number: F3845049620/2020©BEIESP | DOI: 10.35940/ijitee.F3845.049620
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Machine learning in recent years has become an integral part of our day to day life and the ease of use has improved a lot in the past decade. There are various ways to make the model to work in smaller devices. A modest method to advance any machine learning algorithm to work in smaller devices is to provide the output of large complex models as input to smaller models which can be easily deployed into mobile phones .We provided a framework where the large models can even learn the domain knowledge which is integrated as first-order logic rules and explicitly includes that knowledge into the smaller model by simultaneously training of both the models. This can be achieved by transfer learning where the knowledge learned by one model can be used to teach the other model. Domain knowledge integration is the most critical part here and it can be done by using some of the constraint principles where the scope of the data is reduced based upon the constraints mentioned. One of the best representation of domain knowledge is logic rules where the knowledge is encoded as predicates. This framework provides a way to integrate human knowledge into deep neural networks that can be easily deployed into any devices.
Keywords: Algorithms, Ensemble models, First-Order Logic Rules, Deep Neural Networks.
Scope of the Article: Machine Learning (ML) and Knowledge Mining (KM)