Boltzmann machines as two-dimensional tensor networks

05/10/2021
by   Sujie Li, et al.
0

Restricted Boltzmann machines (RBM) and deep Boltzmann machines (DBM) are important models in machine learning, and recently found numerous applications in quantum many-body physics. We show that there are fundamental connections between them and tensor networks. In particular, we demonstrate that any RBM and DBM can be exactly represented as a two-dimensional tensor network. This representation gives an understanding of the expressive power of RBM and DBM using entanglement structures of the tensor networks, also provides an efficient tensor network contraction algorithm for the computing partition function of RBM and DBM. Using numerical experiments, we demonstrate that the proposed algorithm is much more accurate than the state-of-the-art machine learning methods in estimating the partition function of restricted Boltzmann machines and deep Boltzmann machines, and have potential applications in training deep Boltzmann machines for general machine learning tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/24/2021

Tensor networks for unsupervised machine learning

Modeling the joint distribution of high-dimensional data is a central ta...
research
10/11/2017

Neural Networks Quantum States, String-Bond States and chiral topological states

Neural Networks Quantum States have been recently introduced as an Ansat...
research
01/17/2017

On the Equivalence of Restricted Boltzmann Machines and Tensor Network States

Restricted Boltzmann machine (RBM) is one of the fundamental building bl...
research
12/21/2013

Relaxations for inference in restricted Boltzmann machines

We propose a relaxation-based approximate inference algorithm that sampl...
research
12/18/2019

Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physics

Quantum simulators and processors are rapidly improving nowadays, but th...
research
05/11/2015

Soft-Deep Boltzmann Machines

We present a layered Boltzmann machine (BM) that can better exploit the ...
research
04/20/2016

Estimating 3D Trajectories from 2D Projections via Disjunctive Factored Four-Way Conditional Restricted Boltzmann Machines

Estimation, recognition, and near-future prediction of 3D trajectories b...

Please sign up or login with your details

Forgot password? Click here to reset