Loading...

Design an Artificial Neural Structure by Using Mirror Neurons for Implementing the Ink Drop Spread (I.D.S) Operator in Active Learning Method Algorithm

Bashirzadeh, Daniyal | 2017

825 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 49734 (55)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Bagheri Shouraki, Saeed
  7. Abstract:
  8. In this research, a study on Mirror Neuron and Active learning method was done based on the human capability of using their past knowledge in order to understand new systems faster and with more accuracy. Mirror ALM, A new modeling technique based on ALM was proposed that is capable of merging the IDS planes of an old system in order to improve the output of the modeling for a new system. This new technique was tested on a 3D function, state estimation of an inverted pendulum and finally in control procedure of an inverted pendulum. The results of the tests were compared with the classic ALM method to recognize the advantages and disadvantages of the introduced method. The results showed that system is capable of modeling regardless of the incomplete knowledge or improper knowledge with better modeling error than the classical ALM method. The disadvantage of the proposed modeling technique was that it prevents the modeling output to converge to the real answers of the modeling system as the knowledge over the system improves or becomes complete. It means that for a system with improper knowledge the output of the Mirror ALM was better than the outcome of the classical ALM but when the knowledge over the system is complete the output of the classical ALM outclass the results of the Mirror ALM
  9. Keywords:
  10. Ink Drop Spread (IDS)Operator ; Modeling ; Control ; Active Learning ; Neuron ; Mirror Active Learning Method ; Mirror Neuran

 Digital Object List

 Bookmark

No TOC