We gratefully acknowledge support from the Simons Foundation and member institutions. Our automated source to PDF conversion system has failed to produce PDF for the paper: 2312.12909 . Return to the abstract for an alternative link to the source, or to find an email address to contact the author. For help regarding the automated source to PDF system, please contact help@arxiv.org

However, the performance of most equalizers depends on their complexity, leading to power-hungry receivers when implemented on digital hardware. Compared to conventional digital hardware, neuromorphic hardware can massively reduce energy consumption when solving the same tasks [1]. Spiking neural networks (SNNs) implemented on neuromorphic hardware mimic the human brain's behavior and promise energy-efficient, low-latency processing [2]. In [3], an SNN-based equalizer with a decision feedback structure (SNN-DFE) has been proposed for equalization and demapping based on future and currently received, and already decided symbols. For different multipath scenarios, i.e., linear channels, the SNN-DFE performs similarly to the classical decision feedback equalizer (CDFE) and artificial neural network (ANN) based equalizers. For a 4-fold pulse amplitude modulation (PAM4) transmitted over an intensity modulation / direct detection (IM/DD) link suffering from chromatic dispersion (CD) and non-linear impairments, [4] proposes an SNN that estimates the transmit symbols based on received symbols without feedback, no-feedback-SNN (NF-SNN).

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7\% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow---without reconfiguration---reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42\,Gb/s below the HD-FEC threshold at distances beyond 40\,km. We find that our results outperform conventional IM/DD solutions based on 2 and 4 level pulse amplitude modulation (PAM2/PAM4) with feedforward equalization (FFE) at the receiver. Our study is the first step towards end-to-end deep learning-based optimization of optical fiber communication systems.