#	Pagina
attuale pagina	/open-h2020/projects/201335/index.html

Opendata, web and dolomites

DEEPCEPTION

Visual perception in deep neural networks

Total Cost €

EC-Contrib. €

Partnership

Views

Outcomes and
results

DEEPCEPTION project word cloud

Explore the words cloud of the DEEPCEPTION project. It provides you a very rough idea of what is the project "DEEPCEPTION" about.

huge deceptive shortcomings solid lay visual matching battery variety recognize psychologically explaining data foundation algorithms see biologically little turns models capitalizing employ difficult class faces limitations introducing things critically twofold ease shed power tests performance daily supremely humans how deep light despite generation perception human perform broad perceiving nets vision spot behavioral neural computer

Project "DEEPCEPTION" data sheet

The following table provides information about the project.

Coordinator	KATHOLIEKE UNIVERSITEIT LEUVEN Organization address address: OUDE MARKT 13 city: LEUVEN postcode: 3000 website: www.kuleuven.be contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.
Coordinator Country	Belgium [BE]
Project website	https://klab.lt
Total cost	258˙530 €
EC max contribution	258˙530 € (100%)
Programme	1. H2020-EU.1.3.2. (Nurturing excellence by means of cross-border and cross-sector mobility)
Code Call	H2020-MSCA-IF-2015
Funding Scheme	MSCA-IF-GF
Starting year	2016
Duration (year-month-day)	from 2016-10-01 to 2019-09-30

Partnership

Take a look of project's partnership.

#	participants	country	role	EC contrib. [€]
1	KATHOLIEKE UNIVERSITEIT LEUVEN KATHOLIEKE UNIVERSITEIT LEUVEN Organization address address: OUDE MARKT 13 city: LEUVEN postcode: 3000 website: www.kuleuven.be contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	BE (LEUVEN)	coordinator	258˙530.00
2	MASSACHUSSETTS INSTITUTE OF TECHNOLOGY MIT CORPORATION MASSACHUSSETTS INSTITUTE OF TECHNOLOGY MIT CORPORATION Organization address address: MASSACHUSETTS AVENUE 77 city: CAMBRIDGE postcode: 2139 website: n.a. contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	US (CAMBRIDGE)	partner	0.00

Map

Project objective

How do we recognize what we see? Despite the deceptive ease of perceiving things, explaining how we see turns out to be a supremely difficult task. Only recently advances in computer vision finally brought a class of models, known as deep neural nets, that are capable of matching human performance in several visual perception tasks. In this project, we aim to employ the knowledge how human visual system processes visual information in order to critically evaluate and improve the existing models of vision. Our aim is twofold. On the one hand, little is known yet how well deep nets can account for a huge variety of tasks that human visual system faces daily. We will perform a broad battery of tests in order to shed light on the power of deep nets and to spot potential limitations. Capitalizing on these shortcomings, in the second part of this project we aim to improve the existing technology by introducing novel algorithms based on behavioral and neural data of humans. Taken together, this project will lay a solid foundation for the psychologically- and biologically-based development of the next generation of deep nets.

Publications

List of publications.
year	authors and title	journal	last update
2019	Kohitij Kar, Jonas Kubilius, Kailyn Schmidt, Elias B. Issa, James J. DiCarlo Evidence that recurrent circuits are critical to the ventral streamâ€™s execution of core object recognition behavior published pages: 974-983, ISSN: 1097-6256, DOI: 10.1038/s41593-019-0392-5	Nature Neuroscience 22/6	2020-03-17
2019	Jonas Kubilius, Martin Schrimpf, Ha Hong, Najib J. Majaj, Rishi Rajalingham, Elias B. Issa, Kohitij Kar, Pouya Bashivan, Jonathan Prescott-Roy, Kailyn Schmidt, Aran Nayebi, Daniel Bear, Daniel L. K. Yamins, James J. DiCarlo Brain-like object recognition with high-performing shallow recurrent ANNs published pages: , ISSN: , DOI:	Advances in Neural Information Systems 32 (NeurIPS 2019)	2020-03-17
2017	Chengxu Zhuang, Jonas Kubilius, Mitra JZ Hartmann, Daniel L. Yamins Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System published pages: 2555--2565, ISSN: , DOI:	Advances in Neural Information Processing Systems 30 (NIPS 2017)	2020-03-17
2018	Jonas Kubilius Predict, then simplify published pages: 110-111, ISSN: 1053-8119, DOI: 10.1016/j.neuroimage.2017.12.006	NeuroImage 180	2020-03-17
2018	Jonas Kubilius, Martin Schrimpf, Aran Nayebi, Daniel Bear, Daniel L. K. Yamins, James J. DiCarlo CORnet: Modeling the Neural Mechanisms of Core Object Recognition published pages: , ISSN: , DOI: 10.1101/408385	bioRxiv	2020-03-17
2018	Jonas Kubilius, Kohitij Kar, Kailyn Schmidt, James J. DiCarlo Can deep neural networks rival human ability to generalize in core object recognition? published pages: , ISSN: , DOI:	Conference on Cognitive Computational Neuroscience	2020-03-17
2018	Kohitij Kar, Jonas Kubilius, Kailyn M. Schmidt, Elias B. Issa, James J. DiCarlo Evidence that recurrent circuits are critical to the ventral stream\'s execution of core object recognition behavior published pages: , ISSN: , DOI: 10.1101/354753	bioRxiv	2020-03-17
2018	Martin Schrimpf, Jonas Kubilius, Ha Hong, Najib J. Majaj, Rishi Rajalingham, Elias B. Issa, Kohitij Kar, Pouya Bashivan, Jonathan Prescott-Roy, Kailyn Schmidt, Daniel L. K. Yamins, and James J. DiCarlo Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? published pages: , ISSN: , DOI: 10.1101/407007	bioRxiv	2020-03-17
2018	Aran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. Yamins Task-Driven Convolutional Recurrent Models of the Visual System published pages: , ISSN: , DOI:	Advances in Neural Information Processing Systems 31 (NIPS 2018)	2020-03-17

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "DEEPCEPTION" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "DEEPCEPTION" are provided by the European Opendata Portal: CORDIS opendata.