Unsupervised ANN-Based Equalizer and Its Trainable FPGA Implementation
This work addresses the need for flexible and autonomous communication systems by enabling unsupervised adaptation, which is incremental but practical for reducing overhead in real-world applications.
The authors tackled the problem of adapting equalizers in communication systems without pilot symbols by proposing an unsupervised ANN-based equalizer with a custom loss function, achieving performance close to a supervised baseline. They also implemented it on an FPGA, achieving Gbit/s throughput and outperforming a high-performance GPU.
In recent years, communication engineers put strong emphasis on artificial neural network (ANN)-based algorithms with the aim of increasing the flexibility and autonomy of the system and its components. In this context, unsupervised training is of special interest as it enables adaptation without the overhead of transmitting pilot symbols. In this work, we present a novel ANN-based, unsupervised equalizer and its trainable field programmable gate array (FPGA) implementation. We demonstrate that our custom loss function allows the ANN to adapt for varying channel conditions, approaching the performance of a supervised baseline. Furthermore, as a first step towards a practical communication system, we design an efficient FPGA implementation of our proposed algorithm, which achieves a throughput in the order of Gbit/s, outperforming a high-performance GPU by a large margin.