Fig. 2
From: Exploring the GDB-13 chemical space using deep generative models
Example of a forward pass of nicotine (CN1CCCC1c1cccnc1) on a trained model. The symbol sampled from the probability distribution at the step \(i\) (highlighted in black) is input at the step \(i + 1\). This, with the hidden state (hi), enables the model to have time-dynamic behavior. Note that sometimes tokens with lower probability are sampled (like in step 1) due to the multinomial sampling of the model. Also note that the probability distributions are not from real trained models and that the vocabulary used throughout this publication is much bigger