On deep learning-based channel decoding
Top Cited Papers
- 1 March 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We revisit the idea of using deep neural networks for one-shot decoding of random and structured codes, such as polar codes. Although it is possible to achieve maximum a posteriori (MAP) bit error rate (BER) performance for both code families and for short codeword lengths, we observe that (i) structured codes are easier to learn and (ii) the neural network is able to generalize to codewords that it has never seen during training for structured, but not for random codes. These results provide some evidence that neural networks can learn a form of decoding algorithm, rather than only a simple classifier. We introduce the metric normalized validation error (NVE) in order to further investigate the potential and limitations of deep learning-based decoding with respect to performance and complexity.This publication has 17 references indexed in Scilit:
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- An application of neural net in decoding error-correcting codesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- NEURAL NETWORK DECODERS FOR LINEAR BLOCK CODESInternational Journal of Computational Engineering Science, 2002
- An artificial neural net Viterbi decoderIEEE Transactions on Communications, 1996
- On the computational power of neural netsPublished by Association for Computing Machinery (ACM) ,1992
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Neural networks, error-correcting codes, and polynomials over the binary n-cubeIEEE Transactions on Information Theory, 1989
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences of the United States of America, 1982
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943