Deep Learning-Based Decoding of Constrained Sequence Codes

Synchronization of Variable-Length Constrained Sequence Codes

“…We consider the BSC because a BSC is a general channel model that, with appropriate extension, can represent a wide range of scenarios where coded bits are corrupted in digital transmissions due to various factors such as additive noise, fading, interference, etc. The decoding algorithm that we consider is the conventional bit-by-bit decoding algorithm described in the Appendix of [26], and which is reproduced here as Algorithm 2.…”

“…Therefore, we perform partial extensions over the minimal sets to generate larger codebooks. However, different from [20]- [26] where partial extensions are exhaustively performed and the one that has the highest efficiency is selected, in this section we introduce an algorithm that efficiently guides the partial extension process such that the resulting codebook has a high sync probability. Note that performing partial extensions without care can reduce the sync probability, as we show in the following example.…”

“…Since Shannon's 1948 paper [5], the design of CS codes has been an active research area where efficient CS codes that satisfy a great variety of constraints have been proposed. Although most CS codes in the literature are fixed-length codes [1]- [4], [6]- [16], recent advances show that variable-length CS codes have the potential to achieve higher code rates with simpler codebooks [17]- [26]. Since CS codes typically do not have strong error-correction capabilities, decoding of CS codes may result in error propagation.…”

Receiver Design for Faster-Than-Nyquist Signaling: Deep-Learning-Based Architectures

“…In recent years, a new trend has appeared to merge the two technologies of communications and DL [16]- [18]. Nowadays, DL has been widely employed in conventional communication scenarios, such as orthogonal frequency-division multiplexing (OFDM) systems [19]- [21], multi-antenna systems [22], channel estimation and prediction [23]- [25], channel coding [26]- [28], modulation classification [29], etc. However, DL-based receiver design for FTN signaling, as far as we know, has not been studied yet in the literature.…”

Construction of Multi-State Capacity-Approaching Variable-Length Constrained Sequence Codes With State-Independent Decoding

“…Constrained sequence (CS) codes, such as runlength-limited (RLL) codes, DC-free codes and DC-free RLL codes, continue to be studied for application in digital transmission [1]- [4], magnetic and optical recording [5]- [7], non-volatile storage [8]- [11], DNA-based storage systems [12] and visible light communication (VLC) [13]- [18]. Most constrained sequence codes are fixed-length codes, where codebooks consist of source words and codewords of uniform length.…”