Tractable Latent State Inference for Hidden Continuous-Time semi-Markov Chains Supplement Source Code at: https: //anonymous.4open.science/r/BFghJAGII31

Neural Information Processing Systems 

We will first replicate an equation similar to (20) for the backward case. The derivation is similar to that of the forward equation, so that it uses a combination of equations (16), (18) and (19) while leaving out the observation likelihood function. The combination is again carried out using the Laplace transform.