571 citations · 2.8k across the 60 of their papers we have counts for
10 papers · 1 filter
Learning to Skip Ineffectual Recurrent Computations in LSTMs
Arash Ardakani, Zhengyun Ji, Warren J. Gross
Long Short-Term Memory (LSTM) is a special class of recurrent neural network, which has shown remarkable successes in processing sequential data. The typical architecture of an LST…
Neural Belief Propagation Decoding of CRC-Polar Concatenated Codes
Nghia Doan, Seyyed Ali Hashemi, Elie Ngomseu Mambou +2
Polar codes are the first class of error correcting codes that provably achieve the channel capacity at infinite code length. They were selected for use in the fifth generation of…
Learning from the Syndrome
Loren Lugosch, Warren J. Gross
In this paper, we introduce the syndrome loss, an alternative loss function for neural error-correcting decoders based on a relaxation of the syndrome. The syndrome loss penalizes…
Improved Bit-Flipping Algorithm for Successive Cancellation Decoding of Polar Codes
Furkan Ercan, Carlo Condo, Warren J. Gross
The interest in polar codes has been increasing significantly since their adoption for use in the 5 generation wireless systems standard. Successive cancellation (SC) de…
Towards Practical Software Stack Decoding of Polar Codes
Harsh Aurora, Warren J. Gross
The successive cancellation list decoding algorithm for polar codes yields near-optimal decoding performance at the cost of high implementation complexity. The successive cancellat…
Learning Recurrent Binary/Ternary Weights
Arash Ardakani, Zhengyun Ji, Sean C. Smithson +2
Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. Th…