Sparse code multiple access (SCMA) has been one of non-orthogonal multiple access (NOMA) schemes aiming to support high spectral efficiency and ubiquitous access requirements for 5G wireless communication networks. Conventional SCMA approaches are confronting remarkable challenges in designing low complexity high accuracy decoding algorithm and constructing optimum codebooks. Fortunately, the recent spotlighted deep learning technologies are of significant potentials in solving many communication engineering problems. Inspired by this, we explore approaches to improve SCMA performances with the help of deep learning methods. We propose and train a deep neural network (DNN) called DL-SCMA to learn to decode SCMA modulated signals corrupted by additive white Gaussian noise (AWGN). Putting encoding and decoding together, an autoencoder called AE-SCMA is established and trained to generate optimal SCMA codewords and reconstruct original bits. Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed. Simulations show that the DNN SCMA decoder significantly outperforms the conventional message passing algorithm (MPA) in terms of bit error rate (BER), symbol error rate (SER) and computational complexity, and AE-SCMA also demonstrates better performances via constructing better SCMA codebooks. The performance of deep learning aided DCMA is superior to the SCMA.As depicted in Fig. 1, consider J users transmitting data bits over the same K sub-carriers of OFDM, here K < J such that overloading is provided. According to SCMA encoder, each user maps every m = log 2 (M ) bits into a K-dimensional complex codeword c with only N non-zero elements standing for QAM modulation and LDS spreading combination, here N < K. The overlapping degree is d f = JN K , and overloading ratio is λ = J K . There are M codewords forming a codebook for each user and each codebook is unique. The encoding procedure can be described by c = f (b), where b ∈ B log2(M ) and c ∈ C ⊂ C K with |C| = M . Function f is actually a mapping matrix which