Voluntary Behavior on Cortical Learning Algorithm Based Agents

Date

2016-09-23

Author

Sungur, Ali Kaan
Sürer, Elif

Metadata

Show full item record

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

Item Usage Stats

308
views

0
downloads

Operating autonomous agents inside a 3D workspace is a challenging problem domain in real-time for dynamic environments since it involves online interaction with ever-changing decision constraints. This study proposes a neuroscience inspired architecture to simulate autonomous agents with interaction capabilities inside a 3D virtual world. The environment stimulates the operating agents based on their place and course of action. They are expected to form a life cycle composed of behavior chunks inside this environment and continuously optimize it around the stimulated reward. The architecture is composed of specialized units that run Cortical Learning Algorithm (CLA) which models functional properties of layers II and III as in six layer theory of neocortex. This work focuses on extending it with functional properties of layers IV, V and basal ganglia to obtain voluntary behavior that is suitable for an autonomous agent. Through experimental scenarios, the architecture is observed and evaluated in order to obtain an apparent learning process. The communication between layers and internal connectivity of embedded CLA units are able to capture sequential and causal relations from the environment and the first evaluation of the implementation has high potential for future directions.

Subject Keywords

Cortical learning algorithm, Hierarchical temporal memory, Autonomous agent, Neocortex layers, Artificial life

URI

https://hdl.handle.net/11511/55617

Collections

Graduate School of Informatics, Conference / Seminar

Suggestions

OpenMETU
Core

DELAYED DETACHED-EDDY SIMULATION BASED PREDICTIONS OF BOUNDARY LAYER TRANSITION AND CAVITY FLOW NOISE Yalçın, Özgür; Özyörük, Yusuf; Department of Aerospace Engineering (2021-11-1) This dissertation investigates the boundary layer transition as well as the cavity flow noise prediction capabilities of a high-order in-house solver using various Delayed Detached-Eddy Simulation (DDES) frameworks. Before conducting the simulations, multiblock topology with a high-order overset grid technique is implemented into the solver, which makes mesh generation for complex geometries, such as the tunnel grids around blade sections, and cavity grids composed of two separate domains of the studied cas...
Immersive design environments for performative architectural design: a BIM-based approach. Akın, Şahin; Gürsel Dino, İpek; Department of Architecture (2020) In architectural design processes, the use of shared, simulated, and synchronized virtual environments and computational methods becomes widespread. Virtual reality immerses users in a three-dimensional digital environment and has the potential to make them involve actively in the act of design. Daylighting is an essential concept in architectural design, but its assessment and integration to the design process can be complicated. The use of Building Information Modelling (BIM) tools is identified as a crit...
Multiverse of a Form Sorguç, Arzu; Özgenel, Çağlar Fırat (2018-09-21) The almost seamless integration of computation, fabrication and immersion technologies in architecture not only constitutes potentials for exploring design instances through multiple media but also changes design paradigm from form-formation to form-formation-exploration. In this sense, multiverse of design as proposed in this study and integration of various design technologies from virtual to real aims to advance higher-order thinking skills and a more exclusive design exploration in computational design ...
An SRWNN-based approach on developing a self-learning and self-evolving adaptive control system for motion platforms Ari, Evrim Onur; Kocaoglan, Erol (2016-02-01) In this paper, a self-recurrent wavelet neural network (SRWNN)-based indirect adaptive control architecture is modified for performing speed control of a motion platform. The transient behaviour of the original learning algorithm has been improved by modifying the learning rate updates. The contribution of the proposed modification has been verified via both simulations and experiments. Moreover, the performance of the proposed architecture is compared with robust RST designs performed on a similar benchmar...
Optimal posture control algorithm to improve the stability of redundant haptic devices Baser, Ozgur; Konukseven, Erhan İlhan (SAGE Publications, 2013-5-9) Stability is indispensable to haptic interfaces for the simulation of a large variety of virtual environments. On a multi-degree of freedom (multi-DOF) haptic device, the passivity condition must be satisfied in both end-effector and joint space to achieve stable interaction. In this study, a conservative passivity condition is utilized for the stability such that guaranteeing the passivity at all joints is a sufficient condition for the passivity and then stability of the whole haptic system. An optimal po...

Citation Formats

A. K. Sungur and E. Sürer, “Voluntary Behavior on Cortical Learning Algorithm Based Agents,” 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/55617.