2012/03/20 by Guillaume Desjardins, Aaron Courville, Desjardins, Guillaume +3
Computer Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Music and Audio Processing #Neural and Evolutionary Computing (cs.NE) #cs.AI #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.1203.4416
arxiv created 2012/03/20 · openalex publication_date 2012/03/20 · arxiv updated 2012/03/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The deep Boltzmann machine (DBM) has been an important development in the quest for powerful "deep" probabilistic models. To date, simultaneous or joint training of all layers of the DBM has been largely unsuccessful with existing training methods. We introduce a simple regularization scheme that encourages the weight vectors associated with each hidden unit to have similar norms. We demonstrate that this regularization can be easily combined with standard stochastic maximum likelihood to yield an effective training strategy for the simultaneous training of all layers of the deep Boltzmann machine.