Convolutional Deep Exponential Families (2021)

by Chengkuan Hong and Christian R. Shelton

Abstract: We describe convolutional deep exponential families (CDEFs) in this paper. CDEFs are built based on deep exponential families, deep probabilistic models that capture the hierarchical dependence between latent variables. CDEFs greatly reduce the number of free parameters by tying the weights of DEFs. Our experiments show that CDEFs are able to uncover time correlations with a small amount of data.

Download Information

Chengkuan Hong and Christian R. Shelton (2021). "Convolutional Deep Exponential Families." arXiv:2110.14800.

Bibtex citation

@misc{HonShe21b,
     author = "Chengkuan Hong and Christian R. Shelton",
     title = "Convolutional Deep Exponential Families",
     year = 2021,
     month = oct,
     archivePrefix = "arXiv",
     note = "arXiv:2110.14800",
}

---

full list