DeepSig: Deep Learning for Wireless Communications

Originally published at: https://developer.nvidia.com/blog/deepsig-deep-learning-wireless-communications/

Figure 1. The channel autoencoder matches the optimal known solution for BPSK in an AWGN channel The complexity of wireless system design is continually growing. Communications engineering strives to further improve metrics like throughput and interference robustness while simultaneously scaling to support the explosion of low-cost wireless devices. These often-competing needs makes system complexity intractable.…