# Unsupervised ANN-Based Equalizer and Its Trainable FPGA Implementation

arXiv: https://arxiv.org/abs/2304.06987 · HTML: https://mlsanity.com/paper/2304.06987/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 6 of 6)

- [BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization](https://mlsanity.com/paper/2002.03090/) (2020)
- [Artificial Intelligence Enabled Wireless Networking for 5G and Beyond: Recent Advances and Future Challenges](https://mlsanity.com/paper/2001.08159/) (2020)
- [Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems](https://mlsanity.com/paper/2206.12180/) (2022)
- [Wiener Filter for Short-Reach Fiber-Optic Links](https://mlsanity.com/paper/2004.12148/) (2020)
- [FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training](https://mlsanity.com/paper/2212.03515/) (2022)
- [Blind and Channel-agnostic Equalization Using Adversarial Networks](https://mlsanity.com/paper/2209.07277/) (2022)

## Built on by (most cited first, 2 of 2)

- [CNN-Based Equalization for Communications: Achieving Gigabit Throughput with a Flexible FPGA Hardware Architecture](https://mlsanity.com/paper/2405.02323/) (2024)
- [Real-Time FPGA Demonstrator of ANN-Based Equalization for Optical Communications](https://mlsanity.com/paper/2402.15288/) (2024)

## Abstract (arXiv)

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.