A common way to model multiclass classification problems is by means of Error-Correcting Output Codes (ECOCs). Given a multiclass problem, the ECOC technique designs a code word fo...
Sergio Escalera, David M. J. Tax, Oriol Pujol, Pet...
Turbo coding is a powerful class of error correcting codes, which can achieve performances close to the Shannon limit. The turbo principle can be applied to the problem of side-in...
Kim-Chi Nguyen, Gilles Van Assche, Nicolas J. Cerf
It is known that convolutional neural networks (CNNs) are efficient for optical character recognition (OCR) and many other visual classification tasks. This paper applies error-co...
In this paper we re-open a 25 years old question of joint encryption and error-correction coding, named here as Cryptcoding. Cryptcoding is a procedure in which encryption/decrypti...
Danilo Gligoroski, Svein J. Knapskog, Suzana Andov...
In order to achieve fault tolerance, highly reliable system often require the ability to detect errors as soon as they occur and prevent the speared of erroneous information throu...