Low-density parity-check (LDPC) codes, invented by Gallager [2], who described and analyzed a block variant of the codes, arouse great interest of researchers. These codes are widely used in practice since they can be decoded by using relatively simple iterative decoding algorithms. Several modifications of these codes are known, in particular, generalized LDPC codes [3]. In contrast to Gallage...

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an up-convolutional neural network. We apply the method to shallow representations (HOG, SIFT, LBP), as well as to deep networks. For shallow representations our appro...

In this research paper, a novel Convolutional Associative Memory is proposed. In the proposed model, Synapse of each neuron is modeled as a Linear FIR filter. The dynamics of Convolutional Associative Memory is discussed. A new method called SubSampling is given. Proof of convergence theorem is discussed. An example depicting the convergence is shown. Special cases to the proposed convolutional...

In this paper we give a compact presentation of the theory of abstract spaces for convolutional codes and convolutional encoders, and show a connection between them that seems to be missing in the literature. We use it for a short proof of two facts: the size of a convolutional encoder of a polynomial matrix is at least its inner degree, and the minimal encoder has the size of the external degr...

In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts. Our method performs MCTS in batches, explores the Monte Carlo search tree using Thompson sampling and a convolutional network, and evaluates convnet-based rollouts on the GPU. We achieve strong win rates against open source Go programs and attain competitive results against state of the art ...

A rate R = 5/20 hypergraph-based woven convolutional code with overall constraint length 67 and constituent convolutional codes is presented. It is based on a 3-partite, 3uniform, 4-regular hypergraph and contains rate R = 3/4 constituent convolutional codes with overall constraint length 5. Although the code construction is based on low-complexity codes, the free distance of this construction,...

D. J. Costello, Jr., “Free distance bounds for convolutional codes,” IEEE Trans. Inform. Theory, vol. IT-20, pp. 356-365, May 1974. M. Mooser, “Some periodic convolutional codes better than any fixed Code,” IEEE Trans. Inform. Theory, vol. IT-29, pp. 75G751, Sept. 1983. J. L. Massey, “Error bounds for tree codes, trellis codes, and convolutional codes with encoding, and decoding procedures,” CI...

Convolutional neural networks are a technology that combines artificial neural networks and recent deep learning methods. They have been applied to many image recognition tasks and have attracted the attention of the researchers of many countries in recent years. This paper summarizes the latest development of convolutional neural networks and expounds the relative research of image recognition...

For a convolutional encoding and Viterbi decoding system, two insertion/deletion/substitution (IDS) error correcting techniques are presented in this paper. In the first means, by using the pruned convolutional codes, a rate compatible encoding system can adapt the transmission according to the state of the channel having IDS errors. In the second means, a convolutional encoded sequence is deco...

This paper proposes a method for detecting facial regions by combining a Gabor filter and a convolutional neural network. The first stage uses the Gabor filter which extracts intrinsic facial features. As a result of this transformation we obtain four subimages. The second stage of the method concerns the application of the convolutional neural network to these four images. The approach present...