Maximum Entropy Learning with Deep Belief Networks

Payton Lin, Szu-Wei Fu, Syu-Siang Wang, Ying-Hui Lai, Yu Tsao
2016 Entropy  
Conventionally, the maximum likelihood (ML) criterion is applied to train a deep belief network (DBN). We present a maximum entropy (ME) learning algorithm for DBNs, designed specifically to handle limited training data. Maximizing only the entropy of parameters in the DBN allows more effective generalization capability, less bias towards data distributions, and robustness to over-fitting compared to ML learning. Results of text classification and object recognition tasks demonstrate ME-trained
more » ... DBN outperforms ML-trained DBN when training data is limited.
doi:10.3390/e18070251 fatcat:xgfit3w5rvdvdhnrr7bm6ngi5i