Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines

@article{Cheng2018InformationPT,
  title={Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines},
  author={Song Cheng and J. Chen and Lei Wang},
  journal={Entropy},
  year={2018},
  volume={20}
}
  • Song Cheng, J. Chen, Lei Wang
  • Published 2018
  • Computer Science, Medicine, Physics, Mathematics
  • Entropy
We compare and contrast the statistical physics and quantum physics inspired approaches for unsupervised generative modeling of classical data. The two approaches represent probabilities of observed data using energy-based models and quantum states, respectively. Classical and quantum information patterns of the target datasets therefore provide principled guidelines for structural design and learning in these two approaches. Taking the Restricted Boltzmann Machines (RBM) as an example, we… Expand
39 Citations
Quantum-classical generative models for machine learning
  • PDF
From Probabilistic Graphical Models to Generalized Tensor Networks for Supervised Learning
  • 23
  • PDF
Tree Tensor Networks for Generative Modeling
  • 30
  • PDF
Bayesian Tensor Network and Optimization Algorithm for Probabilistic Machine Learning
  • 1
A high-bias, low-variance introduction to Machine Learning for physicists
  • 245
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 101 REFERENCES
Equivalence of restricted Boltzmann machines and tensor network states
  • 138
  • PDF
Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures
  • 26
  • Highly Influential
Unsupervised Generative Modeling Using Matrix Product States
  • 102
  • PDF
A topological insight into restricted Boltzmann machines
  • 51
  • PDF
Quantum Entanglement in Neural Network States
  • 195
  • PDF
Deep Learning the Ising Model Near Criticality
  • 50
  • PDF
Mutual information, neural networks and the renormalization group
  • 84
  • PDF
Learning Thermodynamics with Boltzmann Machines
  • 144
  • PDF
Solving the quantum many-body problem with artificial neural networks
  • 704
  • PDF
...
1
2
3
4
5
...