Stochastic Neural Variational Learning of Noisy-OR Bayesian Networks for Images

Stochastic Neural Variational Learning of Noisy-OR Bayesian Networks for Images
复制标题

图像的噪声或贝叶斯网络的随机神经变分学习

DOI:
10.1145/3505711.3505721
复制
发表时间:
2021
期刊:
Proc. of 2021 The 5th International Conference on Advances in Artificial Intelligence (ICAAI)
影响因子:
--
通讯作者:
Ichisugi Yuuji
Ichisugi Yuuji
中科院分区:
--
文献类型:
--
作者:
Sano Takashi;Ichisugi Yuuji

文献摘要

参考文献

相似文献

贝叶斯网络不仅是有用的因果概率模型,但也有希望作为大脑皮层的模型。本文讨论了贝叶斯网络中的无监督学习问题与噪声或条件概率表。我们采用神经变分推理和学习(NVIL),其中棘手的后验分布近似的神经网络的输出。噪声或贝叶斯网络和后验分布神经网络都被优化,以最大化真实对数似然的变分下界。为了检验所提出的方法的有效性,我们使用MNIST手写数字数据集的噪声或贝叶斯网络的无监督学习。我们证实,具有多达128个潜在变量的噪声或贝叶斯网络可以使用NVIL学习给定的数据集。有趣的是,噪声或贝叶斯网络的潜变量学习了数字图像的片段作为其表示。这些表示比sigmoid信念网络获得的表示更容易解释。
Bayesian networks are not only useful as causal probabilistic models but also promising as models of the cerebral cortex. This paper addresses the problem of unsupervised learning in Bayesian networks with noisy-OR conditional probability tables. We employ neural variational inference and learning (NVIL), in which intractable posterior distribution is approximated by the output of a neural network. Both the noisy-OR Bayesian network and the posterior distribution neural network are optimized to maximize the variational lower bound of the true log-likelihood. To examine the effectiveness of the proposed method, we used the MNIST handwritten digit dataset for unsupervised learning of noisy-OR Bayesian networks. We confirmed that noisy-OR Bayesian networks with up to 128 latent variables can learn the given dataset using NVIL. Interestingly, the latent variables of the noisy-OR Bayesian networks learned fragments of digit images as their representation. These representations are easier to interpret than the representations acquired by sigmoid belief networks.
使用 Auto ML 提高黑色素瘤诊断系统的性能
DOI: --
发表时间: 2023
期刊:
影响因子: --
作者:
Inoue Manabu;Yoshimoto Takeshi;Tanaka Kanta;Koge Junpei;Shiozawa Masayuki;Nishii Tatsuya;Ohta Yasutoshi;Fukuda Tetsuya;Satow Tetsu;Kataoka Hiroharu;Yamagami Hiroshi;Ihara Masafumi;Koga Masatoshi;Mlynash Michael;Albers Gregory W.;Toyoda Kazunori;正木達也・北畠直人・飛塚丈輝・花崎和寿・張 維倫・永岡 隆
通讯作者: 正木達也・北畠直人・飛塚丈輝・花崎和寿・張 維倫・永岡 隆
DOI: 10.1364/josaa.20.001434
发表时间: 2003-07-01
影响因子: 1.9
作者:
Lee, TS;Mumford, D
通讯作者: Mumford, D
受限拟贝叶斯网络作为单个皮质区域计算模型的原型工具
DOI: --
发表时间: 2017
期刊: Workshop on Advanced Methodologies for Bayesian Networks
影响因子: --
作者:
N. Takahashi;Yuuji Ichisugi
通讯作者: Yuuji Ichisugi
DOI: 10.1109/ijcnn.2007.4370951
发表时间: 2007
期刊: 2007 International Joint Conference on Neural Networks
影响因子: --
作者:
Yuuji Ichisugi
通讯作者: Yuuji Ichisugi
DOI: --
发表时间: 2019
期刊: --
影响因子: --
作者:
Geng Ji;Dehua Cheng;Huazhong Ning;Changhe Yuan;Hanning Zhou;Liang Xiong;Erik B. Sudderth
通讯作者: Geng Ji;Dehua Cheng;Huazhong Ning;Changhe Yuan;Hanning Zhou;Liang Xiong;Erik B. Sudderth