Region-based Energy Neural Network for Approximate Inference.

摘要: Region-based free energy was originally proposed for generalized belief propagation (GBP) to improve loopy (loopy BP). In this paper, we propose a neural network based model inference in general Markov random fields (MRFs), which directly minimizes the region-based defined on region graphs. We term our Energy Neural Network (RENN). Unlike message-passing algorithms, RENN avoids iterative message and is faster. Also different from recent deep models, by does not require sampling, works MRFs. can also be employed MRF learning. Our experiments marginal distribution estimation, partition function learning of MRFs show that outperforms mean field method, BP, GBP, state-of-the-art model.