Polar codes, developed on the foundation of Arikan's polarization kernel, represent a breakthrough in coding theory and have emerged as the state-of-the-art error-correction-code in short-to-medium block length regimes.
Inspired by the Markovianity of natural languages, we model the data as a Markovian source and utilize this framework to systematically study the interplay between the data-distributional properties, the transformer architecture, the learnt distribution, and the final model performance.
On the latter, we obtain $50$-$64 \%$ improvement in perplexity over our baselines for noisy channels.
We use our MetaCC benchmark to study several aspects of meta-learning, including the impact of task distribution breadth and shift, which can be controlled in the coding problem.
Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder.
What is more, we investigate prediction quality on different metrics and show that sample efficiency of the predictor-based NAS can be improved by considering binary relations of models and an iterative data selection strategy.
Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks.
1 code implementation • 20 Apr 2020 • Jung-Woo Ha, Kihyun Nam, Jingu Kang, Sang-Woo Lee, Sohee Yang, Hyunhoon Jung, Eunmi Kim, Hyeji Kim, Soojin Kim, Hyun Ah Kim, Kyoungtae Doh, Chan Kyu Lee, Nako Sung, Sunghun Kim
Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services.
We automate HW-CNN codesign using NAS by including parameters from both the CNN model and the HW accelerator, and we jointly search for the best model-accelerator pair that boosts accuracy and efficiency.
Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications.
The better accuracy and complexity compromise, as well as the extremely fast speed of our method makes it suitable for neural network compression.
Designing channel codes under low-latency constraints is one of the most demanding requirements in 5G standards.
The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications.
In this paper, we define rank selection as a combinatorial optimization problem and propose a methodology to minimize network complexity while maintaining the desired accuracy.
We show that creatively designed and trained RNN architectures can decode well known sequential codes such as the convolutional and turbo codes with close to optimal performance on the additive white Gaussian noise (AWGN) channel, which itself is achieved by breakthrough algorithms of our times (Viterbi and BCJR decoders, representing dynamic programing and forward-backward algorithms).
Discovering a correlation from one variable to another variable is of fundamental scientific and practical interest.