Perception Based Design Space Structures for Evolutionary Design Systems

Date

2016-12-17

Author

Abbas, Günsu Merin
Gürsel Dino, İpek

Metadata

Show full item record

Item Usage Stats

58
views

0
downloads

URI

https://hdl.handle.net/11511/88297

Collections

Unverified, Conference / Seminar

Suggestions

OpenMETU
Core

Perception based simplification for binaural room auralisation Hacıhabiboğlu, Hüseyin (null; 2006-06-20)
Gaze based Human Computer Interaction Group Eye Tracking GET Platform Acartürk, Cengiz (null; 2015-10-15)
Vision based range and bearing algorithm for robot swarms Balanji, Hamid Majidi; Turgut, Ali Emre (2018-04-14)
Landmark Based Reward Shaping in Reinforcement Learning with Hidden States Demir, Alper; Cilden, Erkin; Polat, Faruk (2019-01-01) While most of the work on reward shaping focuses on fully observable problems, there are very few studies that couple reward shaping with partial observability. Moreover, for problems with hidden states, where there is no prior information about the underlying states, reward shaping opportunities are unexplored. In this paper, we show that landmarks can be used to shape the rewards in reinforcement learning with hidden states. Proposed approach is empirically shown to improve the learning performance in ter...
CONTEXT BASED SUPER RESOLUTION IMAGE RECONSTRUCTION Turgay, Emre; Akar, Gözde (2009-08-21) In this paper a context based super-resolution (SR) image reconstruction method is proposed. The proposed maximum a-posteriori (MAP) based estimator identifies local gradients and textures for selecting the optimal SR method for the region of interest. Texture segmentation and gradient map estimation are done prior to the reconstruction stage. Gradient direction is used for optimal noise reduction along the edges for non-textured regions. On the other hand, regularization term is cancelled for textured regi...

Citation Formats

G. M. Abbas and İ. Gürsel Dino, “Perception Based Design Space Structures for Evolutionary Design Systems,” 2016, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/88297.