2012/12/12 by Ian Goodfellow, Aaron Courville, Goodfellow, Ian +3
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1212.2686
4 pages
arxiv created 2012/12/12 · arxiv updated 2012/12/13
We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at a time, or do not perform well on classifi- cation tasks.