%0 Journal Article %1 osogami2017boltzmann %A Osogami, Takayuki %D 2017 %K energy-models %T Boltzmann machines and energy-based models %U http://arxiv.org/abs/1708.06008 %X We review Boltzmann machines and energy-based models. A Boltzmann machine defines a probability distribution over binary-valued patterns. One can learn parameters of a Boltzmann machine via gradient based approaches in a way that log likelihood of data is increased. The gradient and Hessian of a Boltzmann machine admit beautiful mathematical representations, although computing them is in general intractable. This intractability motivates approximate methods, including Gibbs sampler and contrastive divergence, and tractable alternatives, namely energy-based models.

@article{osogami2017boltzmann, abstract = {We review Boltzmann machines and energy-based models. A Boltzmann machine defines a probability distribution over binary-valued patterns. One can learn parameters of a Boltzmann machine via gradient based approaches in a way that log likelihood of data is increased. The gradient and Hessian of a Boltzmann machine admit beautiful mathematical representations, although computing them is in general intractable. This intractability motivates approximate methods, including Gibbs sampler and contrastive divergence, and tractable alternatives, namely energy-based models.}, added-at = {2019-12-18T16:39:17.000+0100}, author = {Osogami, Takayuki}, biburl = {https://www.bibsonomy.org/bibtex/22a6cbb30369b779350519ddbd4e10c78/kirk86}, description = {[1708.06008] Boltzmann machines and energy-based models}, interhash = {721dbd3ff2a268d4d310890f7ecb7ad8}, intrahash = {2a6cbb30369b779350519ddbd4e10c78}, keywords = {energy-models}, note = {cite arxiv:1708.06008Comment: 36 pages. The topics covered in this paper are presented in Part I of IJCAI-17 tutorial on energy-based machine learning. https://researcher.watson.ibm.com/researcher/view_group.php?id=7834}, timestamp = {2019-12-18T16:39:17.000+0100}, title = {Boltzmann machines and energy-based models}, url = {http://arxiv.org/abs/1708.06008}, year = 2017 }