Andreas Jodhinata
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Andreas Jodhinata has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Agustinus Bimo Gumelar
Universitas Narotama Surabaya
1 shared publication - Fardani Annisa Damastuti
Department of Creative Multimedia Technology, Electronic Engineering Polytechnic Institute of Surabaya
1 shared publication Kenan Firmansyah
1 shared publication- Mauridhi Hery Purnomo
Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
1 shared publication - Mochamad Hariadi
Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia | Department of Computer Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
1 shared publication
Latest Publications
- 29 October 2026
- Published by Elsevier in Entertainment Computing
- Vol. 59
Inference-time personality control for LLM-based game NPCs: A multi-seed study of behavioral consistency and player steering
- 29 October 2026
- Published by Elsevier in Entertainment Computing
- Vol. 59
Inference-time personality control for LLM-based game NPCs: A multi-seed study of behavioral consistency and player steering
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1028-1032
Controlling the hidden layers' output to optimizing the training process in the Deep Neural Network algorithm
Deep learning is one of the most recent development form of Artificial Neural Network (ANN) in machine learning. Deep Neural Network (DNN) algorithm is usually used in image and speech recognition applications. As the development of Artificial Neural Network, very possible there are so many hidden layers in Deep Neural Network. In DNN, the output of each node is a quadratic function of its inputs. The DNN training process is very difficult. In this paper, we try to optimizing the training process by slightly construct of the deep architecture and combines several existing algorithms. Output's error of each unit in the previous layer will be calculated. The weight of the unit with the smallest error will be maintained in the next iteration. This paper uses MNIST handwriting images as its data training and data test. After doing some tests, it can be concluded that the optimization by selecting any output in each hidden layer, the DNN training process will be faster approximately 8%.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1028-1032
Controlling the hidden layers' output to optimizing the training process in the Deep Neural Network algorithm
Deep learning is one of the most recent development form of Artificial Neural Network (ANN) in machine learning. Deep Neural Network (DNN) algorithm is usually used in image and speech recognition applications. As the development of Artificial Neural Network, very possible there are so many hidden layers in Deep Neural Network. In DNN, the output of each node is a quadratic function of its inputs. The DNN training process is very difficult. In this paper, we try to optimizing the training process by slightly construct of the deep architecture and combines several existing algorithms. Output's error of each unit in the previous layer will be calculated. The weight of the unit with the smallest error will be maintained in the next iteration. This paper uses MNIST handwriting images as its data training and data test. After doing some tests, it can be concluded that the optimization by selecting any output in each hidden layer, the DNN training process will be faster approximately 8%.