Not yet reviewed by Pith; the record is open.

We examine encoding and decoding of transmitted sequences for the downlink time-offset faster than Nyquist signaling non-orthogonal multiple access NOMA (T-NOMA) channel. We employ a previously proposed singular value decomposition (SVD)-based scheme as a benchmark. While this SVD scheme provides reliable communication, our findings reveal that it is not optimal in terms of bit error rate (BER). Additionally, the SVD is sensitive to timing offset errors, and its time complexity increases quadratically with the sequence length. We propose a convolutional neural network (CNN) auto-encoder (AE) for encoding and decoding with linear time complexity. We explain the design of the encoder and decoder architectures and the training criteria. By examining several variants of the CNN AE, we show that it can achieve an excellent trade-off between performance and complexity. The proposed CNN AE surpasses the SVD method by approximately 2 dB in a T-NOMA system with no timing offset errors or channel state information estimation errors. In the presence of channel state information (CSI) error variance of 1$\%$ and uniform timing error at $\pm$4\% of the symbol interval, the proposed CNN AE provides up to 10 dB SNR gain over the SVD method. We also propose a novel modified training objective function consisting of a linear combination of the traditionally used cross-entropy (CE) loss function and a closed-form expression for the bit error rate (BER) called the Q-loss function. Simulations show that the modified loss function achieves SNR gains of up to 1 dB over the CE loss function alone.