AI translates chemistry to predict reaction outcomes

By Katrina Krämer2017-12-07T09:09:00

The famous Hochreiter and Schmidhuber LSTM (Long Short Term Memory), a type of recurrent neural network which was used in the paper “Found in Translation”: Predicting Outcomes of Complex Organic Chemistry Reactions

Source: IMB

Machine learning tool predicts products of organic reactions by treating chemistry like language

IBM researchers have developed a program that can predict the products of organic chemistry reactions.¹ Modelled on the latest language translation systems – like Google’s artificial neural network – the AI guesses the right product 80% of the time despite not having been taught any organic chemistry rules.