Pembuatan Survival Action Game Dengan Non-Player Character Berbasis Neural Network

Authors

  • Semuel Yootje Daniel Tawas Program Studi Teknik Informatika
  • Gregorius Satia Budhi Program Studi Teknik Informatika
  • Kristo Radion Purba Program Studi Teknik Informatika

Keywords:

Manager’s Attitude, NEP, environmental management, sector, regional, and Firm Size

Abstract

Game is a multi media application that need some main parts such as, goal, challenge and game play or usually has been know as rules in a game.

Survival action game will apply real time system in its game play. Real time game usually needs fast decision making method for artificial intelligence, so it can’t interrupt any system in the game.

Backpropagation is one of the fastest method that can be used to process data for decision making. Backpropagation method can use data training transformation feature so outputs from backpropagate calculation can be different than before. In its application, backpropagation needs to applying winner-take-all architecture so backpropagation system, can run the training process nicely.

Based on testing result, backpropagation system can be applied in real time game and data training addition feature can gives the transformation for making decision that can be different than before.

References

[1] Dai, Qun. 2012. Back-propagation with diversive curiosity: An automatic conversion from search stagnation to exploration. Jurnal Applied Soft Computing, Vol. 13, pp. 483-495.

[2] Hrasko, Rafael., Pacheco, Andr´e G. C., Krohling, Renato A. 2015. Time Series Prediction using Restricted Boltzmann Machines and Backpropagation. Procedia Computer Science, Vol. 55, pp. 990-999.

[3] Jones, M. T. 2005. AI Application Programming Second Edition. Boston: Charles River Media.

[4] Khadse, C. B., Chaudhari, M. A., Borghate, V. B. 2016. Conjugate gradient back-propagation based artificial neural network for real time power quality assessment. International Journal of Electrical Power & Energy Systems, Vol. 82, pp. 197–206.

[5] Murru, N., Rossini, R. 2016. A Bayesian approach for initialization of weights in backpropagation neural net with application to character recognition. Neurocomputing, Vol. 38, pp. 4967–4971.

[6] Singh, Bikesh K., Verma, K., Thoke, A. S. 2015. Adaptive gradient descent backpropagation for classification of breast tumors in ultrasound imaging. Procedia Computer Science, Vol. 46, pp. 1601-1609.

Downloads

Published

2016-07-31

Issue

Section

Articles