End-to-end Learning of Latent Dirichlet Allocation by Mirror-Descent Back Propagation.
Jianshu ChenJi HeYelong ShenLin XiaoXiaodong HeJianfeng GaoXinying SongLi DengPublished in: CoRR (2015)
Keyphrases
- end to end
- back propagation
- learning algorithm
- latent dirichlet allocation
- neural nets
- topic models
- cascade correlation
- feed forward
- artificial neural networks
- weight update
- neural network
- learning process
- reinforcement learning
- feature extraction
- error back propagation
- multilayer neural network
- prior knowledge
- text mining
- gibbs sampling
- optical flow
- bayesian networks
- genetic algorithm
- multi layer
- topic modeling