Component Training of Turbo Autoencoders

05/16/2023
by   Jannis Clausius, et al.
0

Isolated training with Gaussian priors (TGP) of the component autoencoders of turbo-autoencoder architectures enables faster, more consistent training and better generalization to arbitrary decoding iterations than training based on deep unfolding. We propose fitting the components via extrinsic information transfer (EXIT) charts to a desired behavior which enables scaling to larger message lengths (k ≈ 1000) while retaining competitive performance. To the best of our knowledge, this is the first autoencoder that performs close to classical codes in this regime. Although the binary cross-entropy (BCE) loss function optimizes the bit error rate (BER) of the components, the design via EXIT charts enables to focus on the block error rate (BLER). In serially concatenated systems the component-wise TGP approach is well known for inner components with a fixed outer binary interface, e.g., a learned inner code or equalizer, with an outer binary error correcting code. In this paper we extend the component training to structures with an inner and outer autoencoder, where we propose a new 1-bit quantization strategy for the encoder outputs based on the underlying communication problem. Finally, we discuss the model complexity of the learned components during design time (training) and inference and show that the number of weights in the encoder can be reduced by 99.96

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/29/2021

Serial vs. Parallel Turbo-Autoencoders and Accelerated Training for Learned Channel Codes

Attracted by its scalability towards practical codeword lengths, we revi...
research
02/28/2020

High Rate Communication over One-Bit Quantized Channels via Deep Learning and LDPC Codes

This paper proposes a method for designing error correction codes by com...
research
04/16/2021

Autoencoder-Based Unequal Error Protection Codes

We present a novel autoencoder-based approach for designing codes that p...
research
09/24/2019

Autoencoder-Based Error Correction Coding for One-Bit Quantization

This paper proposes a novel deep learning-based error correction coding ...
research
05/07/2023

Interpreting Training Aspects of Deep-Learned Error-Correcting Codes

As new deep-learned error-correcting codes continue to be introduced, it...
research
07/25/2023

On the Error-Reducing Properties of Superposition Codes

Next-generation wireless communication systems impose much stricter requ...
research
10/23/2018

Learning from the Syndrome

In this paper, we introduce the syndrome loss, an alternative loss funct...

Please sign up or login with your details

Forgot password? Click here to reset