Equivalence of restricted Boltzmann machines and tensor network states

@article{Chen2018EquivalenceOR,
  title={Equivalence of restricted Boltzmann machines and tensor network states},
  author={J. Chen and Song Cheng and Haidong Xie and L. Wang and T. Xiang},
  journal={Physical Review B},
  year={2018},
  volume={97},
  pages={085104}
}
The restricted Boltzmann machine (RBM) is one of the fundamental building blocks of deep learning. RBM finds wide applications in dimensional reduction, feature extraction, and recommender systems via modeling the probability distributions of a variety of input data including natural images, speech signals, and customer ratings, etc. We build a bridge between RBM and tensor network states (TNS) widely used in quantum many-body physics research. We devise efficient algorithms to translate an RBM… Expand
138 Citations
Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
  • 43
  • PDF
Matrix Product Operator Restricted Boltzmann Machines
  • 2
  • PDF
Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
  • 39
  • PDF
Supervised learning with generalized tensor networks
  • 21
Quantum-Classical Machine learning by Hybrid Tensor Networks
  • 2
  • PDF
Tree Tensor Networks for Generative Modeling
  • 30
  • PDF
From Probabilistic Graphical Models to Generalized Tensor Networks for Supervised Learning
  • 23
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 87 REFERENCES
On the Expressive Power of Deep Learning: A Tensor Analysis
  • 253
A topological insight into restricted Boltzmann machines
  • 51
  • Highly Influential
  • PDF
An exact mapping between the Variational Renormalization Group and Deep Learning
  • 220
  • Highly Influential
  • PDF
Unsupervised Generative Modeling Using Matrix Product States
  • 102
  • PDF
Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
  • 72
  • PDF
TensorFlow: A system for large-scale machine learning
  • 9,162
  • PDF
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
  • 589
  • PDF
Quantum Entanglement in Neural Network States
  • 195
  • PDF
Why Does Deep and Cheap Learning Work So Well?
  • 385
  • PDF
...
1
2
3
4
5
...