Fig. 2From: Quantum walk neural networks with feature dependent coinsQuantum walk neural network diagram. The feature matrix X is used by the banks to produce the coin matrices C used in each step layer as well in the final diffusion process. The superposition Φ evolves after each step of the walk. The diffusion layer diffuses X using each superposition {Φ(0),Φ(1),...Φ(T)} and concatenates the results to produce the output YBack to article page