Výsledky vyhledávání - "Duffy, Nigel"

Report

DeepPSL: End-to-end perception and reasoning

Autor: Dasaratha, Sridhar, Puranam, Sai Akhil, Phogat, Karmvir Singh, Tiyyagura, Sunil Reddy, Duffy, Nigel P.

We introduce DeepPSL a variant of probabilistic soft logic (PSL) to produce an end-to-end trainable system that integrates reasoning and perception. PSL represents first-order logic in terms of a convex graphical model -- hinge-loss Markov random fie

Externí odkaz: http://arxiv.org/abs/2109.13662

Zobrazit plný text záznamu

Report

End-to-End Unsupervised Document Image Blind Denoising

Autor: Gangeh, Mehrdad J, Plata, Marcin, Motahari, Hamid, Duffy, Nigel P

Removing noise from scanned pages is a vital step before their submission to the optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However, this assump

Externí odkaz: http://arxiv.org/abs/2105.09437

Zobrazit plný text záznamu

Report

DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction

Autor: Chua, Freddy C., Duffy, Nigel P.

We address the challenge of extracting structured information from business documents without detailed annotations. We propose Deep Conditional Probabilistic Context Free Grammars (DeepCPCFG) to parse two-dimensional complex documents and use Recursi

Externí odkaz: http://arxiv.org/abs/2103.05908

Zobrazit plný text záznamu

Report

Evolving Deep Neural Networks

Autor: Miikkulainen, Risto, Liang, Jason, Meyerson, Elliot, Rawal, Aditya, Fink, Dan, Francon, Olivier, Raju, Bala, Shahrzad, Hormoz, Navruzyan, Arshak, Duffy, Nigel, Hodjat, Babak

The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT,

Externí odkaz: http://arxiv.org/abs/1703.00548

Zobrazit plný text záznamu