Neuro Humanities Studies

Last paper:

Grazia Pulvirenti, Renata Gambino, The paradox of Romantic ekphrasis. Metacritic discourse, perception and imagination in art descripti

Ekphrasis is a text genre based on the intertwining of visual and verbal features, involving the processes of both reading, and priming a visual image or a related action. We argue in this study that...

Read More

Saulius J. Garalevicius,

Memory–Prediction Framework for Pattern Recognition: Performance and Suitability of the Bayesian Mod

Source: American Association for Artif
Year: 2007

Download size: 300.31 KB
This paper explores an inferential system for recognizing visual patterns. The system is inspired by a recent memory-prediction theory and models the high-level architecture of the human neocortex. The paper describes the hierarchical architecture and recognition performance of this Bayesian model. A number of possibilities are analyzed for bringing the model closer to the theory, making it uniform, scalable, less biased and able to learn a larger variety of images and their transformations. The effect of these modifications on recognition accuracy is explored. We identify and discuss a number of both conceptual and practical challenges to the Bayesian approach as well as missing details in the theory that are needed to design a scalable and universal model.


The Neuro Humanities Studies Network aims at creating a multidisciplinary research community in order to develop and structure a linking platform for neuro-scientific, cognitive topics and humanities.

Click on each keyword to show papers related with it.

Research Network

Click on each point to show researchers involved. For more information about our research network, please check the Members section in the menu bar.
e-read logo

NHS Community Calendar