当前位置: X-MOL 学术Sci. Rep. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Mode-assisted joint training of deep Boltzmann machines
Scientific Reports ( IF 4.6 ) Pub Date : 2021-09-24 , DOI: 10.1038/s41598-021-98404-y
Haik Manukian 1 , Massimiliano Di Ventra 1
Affiliation  

The deep extension of the restricted Boltzmann machine (RBM), known as the deep Boltzmann machine (DBM), is an expressive family of machine learning models which can serve as compact representations of complex probability distributions. However, jointly training DBMs in the unsupervised setting has proven to be a formidable task. A recent technique we have proposed, called mode-assisted training, has shown great success in improving the unsupervised training of RBMs. Here, we show that the performance gains of the mode-assisted training are even more dramatic for DBMs. In fact, DBMs jointly trained with the mode-assisted algorithm can represent the same data set with orders of magnitude lower number of total parameters compared to state-of-the-art training procedures and even with respect to RBMs, provided a fan-in network topology is also introduced. This substantial saving in number of parameters makes this training method very appealing also for hardware implementations.



中文翻译:

深度玻尔兹曼机的模式辅助联合训练

受限玻尔兹曼机 (RBM) 的深度扩展,称为深度玻尔兹曼机 (DBM),是一组富有表现力的机器学习模型,可用作复杂概率分布的紧凑表示。然而,在无监督环境中联合训练 DBM已被证明是一项艰巨的任务。我们最近提出的一种称为模式辅助训练的技术在改进 RBM 的无监督训练方面取得了巨大成功。在这里,我们展示了模式辅助训练的性能提升对于 DBM 来说更为显着。事实上,与模式辅助算法联合训练的 DBM 可以以数量级表示相同的数据集如果还引入了扇入网络拓扑,与最先进的训练程序相比,甚至与 RBM 相比,总参数的数量更少。参数数量的大量节省使得这种训练方法对于硬件实现也非常有吸引力。

更新日期:2021-09-24
down
wechat
bug