Bayesian Sparsification Methods for Deep Complex-valued Networks

03/25/2020
by   Ivan Nazarov, et al.
0

With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural complex domain representation. To this end we extend Sparse Variational Dropout to complex-valued neural networks and verify the proposed Bayesian technique by conducting a large numerical study of the performance-compression trade-off of C-valued networks on two tasks: image recognition on MNIST-like and CIFAR10 datasets and music transcription on MusicNet. We replicate the state-of-the-art result by Trabelsi et al. [2018] on MusicNet with a complex-valued network compressed by 50-100x at a small performance penalty.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/14/2022

Fully complex-valued deep learning model for visual perception

Deep learning models operating in the complex domain are used due to the...
research
10/01/2013

The complex-valued encoding for dicision-making based on aliasing data

It is proposed a complex valued channel encoding for multidimensional da...
research
02/25/2021

Quantitative approximation results for complex-valued neural networks

We show that complex-valued neural networks with the modReLU activation ...
research
12/20/2013

Neuronal Synchrony in Complex-Valued Deep Networks

Deep learning has recently led to great successes in tasks such as image...
research
12/02/2021

Co-domain Symmetry for Complex-Valued Deep Learning

We study complex-valued scaling as a type of symmetry natural and unique...
research
08/22/2011

Sparse Estimation using Bayesian Hierarchical Prior Modeling for Real and Complex Linear Models

In sparse Bayesian learning (SBL), Gaussian scale mixtures (GSMs) have b...
research
11/29/2018

Utilizing Complex-valued Network for Learning to Compare Image Patches

At present, the great achievements of convolutional neural network(CNN) ...

Please sign up or login with your details

Forgot password? Click here to reset