Complex Amplitude-Phase Boltzmann Machines

by   Zengyi Li, et al.

We extend the framework of Boltzmann machines to a network of complex-valued neurons with variable amplitudes, referred to as Complex Amplitude-Phase Boltzmann machine (CAP-BM). The model is capable of performing unsupervised learning on the amplitude and relative phase distribution in complex data. The sampling rule of the Gibbs distribution and the learning rules of the model are presented. Learning in a Complex Amplitude-Phase restricted Boltzmann machine (CAP-RBM) is demonstrated on synthetic complex-valued images, and handwritten MNIST digits transformed by a complex wavelet transform. Specifically, we show the necessity of a new amplitude-amplitude coupling term in our model. The proposed model is potentially valuable for machine learning tasks involving complex-valued data with amplitude variation, and for developing algorithms for novel computation hardware, such as coupled oscillators and neuromorphic hardware, on which Boltzmann sampling can be executed in the complex domain.


page 2

page 5

page 6

page 7

page 8

page 12

page 15


Complex-Valued Restricted Boltzmann Machine for Direct Speech Parameterization from Complex Spectra

This paper describes a novel energy-based probabilistic distribution tha...

Gamma Boltzmann Machine for Simultaneously Modeling Linear- and Log-amplitude Spectra

In audio applications, one of the most important representations of audi...

Modeling Image Structure with Factorized Phase-Coupled Boltzmann Machines

We describe a model for capturing the statistical structure of local amp...

Widely Linear Complex-valued Autoencoder: Dealing with Noncircularity in Generative-Discriminative Models

We propose a new structure for the complex-valued autoencoder by introdu...

Complex-valued image denosing based on group-wise complex-domain sparsity

Phase imaging and wavefront reconstruction from noisy observations of co...

Emergence of Compositional Representations in Restricted Boltzmann Machines

Extracting automatically the complex set of features composing real high...

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

Accompanied by the successful progress of deep representation learning, ...

Please sign up or login with your details

Forgot password? Click here to reset