Reinforcement learning in random neural networks for cascaded decisions

Date

1997-01-01

Author

Halıcı, Uğur

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

232
views

0
downloads

The Random Neural Network (RNN) model, in which signals travel as voltage spikes rather than as fixed signal levels, represents more closely the manner in which signals are transmitted in biophysical neural networks. In this paper a reinforcement learning strategy is proposed to make a sequence of cascaded decisions to achieve a goal while aiming to optimize the total cost of the cascaded decisions. For this purpose, RANs are used to model the system and a weight update rule together with a reinforcement function is provided. The performance of the learning strategy is analysed by applying it to the maze learning problem. The simulation results show that the performance of the system is highly dependent on the chosen reinforcement function and quite satisfactory results are obtained when the reinforcement function takes the recency effect into consideration.

Subject Keywords

Random neural networks, Reinforcement learning, Mazes, Recency effect

URI

https://hdl.handle.net/11511/39223

Journal

BioSystems

DOI

https://doi.org/10.1016/0303-2647(96)01633-4

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Neural networks with piecewise constant argument and impact activation Yılmaz, Enes; Akhmet, Marat; Department of Scientific Computing (2011) This dissertation addresses the new models in mathematical neuroscience: artificial neural networks, which have many similarities with the structure of human brain and the functions of cells by electronic circuits. The networks have been investigated due to their extensive applications in classification of patterns, associative memories, image processing, artificial intelligence, signal processing and optimization problems. These applications depend crucially on the dynamical behaviors of the networks. In t...
Measurement correction of a set of analog sun sensors via neural network Sozen, Semsettin Numan; Gokce, Murat; Yavuzyilmaz, Cagatay; Gulmammadov, Farid; Söken, Halil Ersin (2021-06-23) A Neural Network (NN) based method to improve the accuracy of a set of analog Sun sensors is presented. Analog Sun Sensors are commonly used on satellites due to their reduced cost, small size and low power consumption. However, especially in Earth imaging satellites, they are prone to the Earth albedo effects. Magnitude and direction of albedo change depending on the reflection characteristics of the Earth's surface, position and attitude of the satellite and position of the Sun. The albedo may deteriorate...
Optimizing age of information on real-life TCP/IP connections through reinforcement learning Sert, Egemen; Sonmez, Canberk; Baghaee, Sajjad; Uysal, Elif (2018-07-05) Age of Information (AoI) has emerged as a performance metric capturing the freshness of data for status-update based applications ( e.g. , remote monitoring) as a more suitable alternative to classical network performance indicators such as throughput or delay. Optimizing AoI often requires distinctly novel and sometimes counter-intuitive networking policies that adapt the rate of update transmissions to the randomness in network resources. However, almost all previous work on AoI to data has been theoretic...
Spatio-temporal Characteristics of Point and Field Sources in Wireless Sensor Networks Vuran, Mehmet C.; Akan, Ozgur B. (2006-06-15) Wireless Sensor Networks (WSN) are comprised of densely deployed sensor nodes collaboratively observing and communicating extracted information about a physical phenomenon. Dense deployment of sensor nodes makes the sensor observations highly correlated in the space domain. In addition, consecutive samples obtained by a sensor node are also temporally correlated for the applications involving the observation of the variation of a physical phenomenon. Based on the physical characteristics and dispersion patt...
Classical analysis of time behavior of radiation fields associated with biophoton signals Choi, Jeong Ryeol; Kim, Daeyeoul; Menouar, Salah; Sever, Ramazan; Abdalla, M. Sebawe (2016-01-01) BACKGROUND: Propagation of photon signals in biological systems, such as neurons, accompanies the production of biophotons. The role of biophotons in a cell deserves special attention because it can be applied to diverse optical systems.

Citation Formats

U. Halıcı, “Reinforcement learning in random neural networks for cascaded decisions,” BioSystems, pp. 83–91, 1997, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/39223.