Abstract | ||
---|---|---|
Surprise describes a range of phenomena from unexpected events to behavioral responses. We propose a novel measure of surprise and use it for surprise-driven learning. Our surprise measure takes into account data likelihood as well as the degree of commitment to a belief via the entropy of the belief distribution. We find that surprise-minimizing learning dynamically adjusts the balance between ne... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1162/neco_a_01025 | Neural Computation |
Field | DocType | Volume |
Psychology,Artificial intelligence,Unexpected events,Surprise,Machine learning | Journal | 30 |
Issue | ISSN | Citations |
1 | 0899-7667 | 1 |
PageRank | References | Authors |
0.36 | 18 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohammad Javad Faraji | 1 | 57 | 3.69 |
Kerstin Preuschoff | 2 | 20 | 3.23 |
Wulfram Gerstner | 3 | 2437 | 410.08 |