Unit-level surprise in neural networks
To adapt to changes in real-world data distributions, neural networks must update their parameters. We argue that unit-level surprise should be useful for: (i) determining which few parameters should update to adapt quickly; and (ii) learning a modularization such that few modules need be adapted to transfer. We empirically validate (i) in simple settings and reflect on the challenges and opportunities of realizing both (i) and (ii) in more general settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems
A community of researchers appears to think that a machine can be surprised and have introduced various surprise measures, principally the Shannon Surprise and the Bayesian Surprise. The questions of what constitutes a s…
Limits to Surprise in Recommender Systems
In this study, we address the challenge of measuring the ability of a recommender system to make surprising recommendations. Although current evaluation methods make it possible to determine if two algorithms can make re…
Recommendation SystemsCommunity detection in weighted brain connectivity networks beyond the resolution limit
Graph theory provides a powerful framework to investigate brain functional connectivity networks and their modular organization. However, most graph-based methods suffer from a fundamental resolution limit that may have …
Community DetectionFunctional ConnectivityTopic-Level Bayesian Surprise and Serendipity for Recommender Systems
A recommender system that optimizes its recommendations solely to fit a user's history of ratings for consumed items can create a filter bubble, wherein the user does not get to experience items from novel, unseen catego…
Collaborative FilteringRecommendation SystemsLearning in Volatile Environments with the Bayes Factor Surprise
Surprise-based learning allows agents to rapidly adapt to non-stationary stochastic environments characterized by sudden changes. We show that exact Bayesian inference in a hierarchical model gives rise to a surprise-mod…
Bayesian InferenceReinforcement Learning