Joint Training of Deep Boltzmann Machines
arXiv: Machine Learning(2012)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络