Information encoding in the nervous system is supported through the precise spike-timings of neurons; however, an understanding of the underlying processes by which such representations are formed in the first place remains unclear. Here we examine how networks of spiking neurons can learn to encode for input patterns using a fully temporal coding scheme. To this end, we introduce a learning rule for spiking networks containing hidden neurons which optimizes the likelihood of generating desired output spiking patterns. We show the proposed learning rule allows for a large number of accurate input-output spike pattern mappings to be learnt, which outperforms other existing learning rules for spiking neural networks: both in the number of mappings that can be learnt as well as the complexity of spike train encodings that can be utilised. The learning rule is successful even in the presence of input noise, is demonstrated to solve the linearly non-separable XOR computation and generalizes well on an example dataset. We further present a biologically plausible implementation of backpropagated learning in multilayer spiking networks, and discuss the neural mechanisms that might underlie its function. Our approach contributes both to a systematic understanding of how pattern encodings might take place in the nervous system, and a learning rule that displays strong technical capability.