Sequence Classification Restricted Boltzmann Machines With Gated Units
By Son Dinh Tran, A.S. d'Avila Garcez, Tillman Weyde, Jie Yin, Qing Zhang, M. Karunanithi. 2020
8 citations recorded by the source corpus.
For the classification of sequential data, dynamic Bayesian networks and recurrent neural networks (RNNs) are the preferred models. While the former can explicitly model the temporal dependences between the variables, and the latter have the capability of learning representations. The recurrent temporal restricted Boltzmann machine (RTRBM) is a model that combines these two features. However, learning and inference in RTRBMs can be difficult because of the exponential nature of its gradient computations when maximizing log likelihoods. In this article, first, we address this intractability by optimizing a conditional rather than a joint probability distribution when performing sequence classification. This results in the “sequence classification restricted Boltzmann machine” (SCRBM). Second, we introduce gated SCRBMs (gSCRBMs), which use an information processing gate, as an integration of SCRBMs with long short-term memory (LSTM) models. In the experiments reported in this article, we evaluate the proposed models on optical character recognition, chunking, and multiresident activity recognition in smart homes. The experimental results show that gSCRBMs achieve the performance comparable to that of the state of the art in all three tasks. gSCRBMs require far fewer parameters in comparison with other recurrent networks with memory gates, in particular, LSTMs and gated recurrent units (GRUs).
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- François Soumis
- Yassine Yaakoubi
- Simon Lacoste-Julien
- Peter Richtárik
- Francis R. Bach
- Fabian Pedregosa
- Martin Jaggi
- Gauthier Gidel
In Computer Vision and Pattern Recognition
- Simon Lacoste-Julien
- François Soumis
- Yassine Yaakoubi
- Peter Richtárik
- Ivan Laptev
- Gauthier Gidel
- Andrew Zisserman
- Cordelia Schmid
In Model Architectures
Citations in the corpus
- Structured Convolutional Kernel Networks for Airline Crew Scheduling (2021, methodology): “Finally, note that we use a batch-version of the Struct-CKN predictor on the flight-connection dataset (Yaakoubi et al., 2019), where one batch corresponds to one CRF model (Chu et al., 2016) 4.5 SCRBM (Tran et al., 2020) 4.0 NLStruct (Graber et al., 2018) 3.6 Struct-CKN 3.4 (CPP instance): (1) We in”