ANALOGY-BASED REASONING WITH MEMORY NETWORKS FOR FUTURE PREDICTION
Daniel Andrade, Bing Bai, Ramkumar Rajendran, Yotaro Watanabe · Neural Information Processing Systems · 2016
A method is provided that includes accessing a training set of positive and negative event pairs. The method includes calculating (i) positive similarity scores between an input pair of events and the positive event pairs, and (ii) negative similarity scores between the input pair of events and the negative event pairs. The method includes applying a Softmax process to (i) the positive similarity scores to produce an overall positive similarity score for the input pair of events, and (ii) the negative similarity scores to produce an overall negative similarity score for the input pair of events. The method includes calculating the difference between the overall positive and negative similarity scores to obtain a future event prediction score indicating a future occurrence likelihood of at least one of two events forming the input pair of events. The method includes performing an action responsive to the future event prediction score.