RandNet: deep learning with compressed measurements of images

08/25/2019
by   Thomas Chang, et al.
0

Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the longer it takes to learn. We introduce a class of neural networks, termed RandNet, for learning representations using compressed random measurements of data of interest, such as images. RandNet extends the convolutional recurrent sparse auto-encoder architecture to dense networks and, more importantly, to the case when the input data are compressed random measurements of the original data. Compressing the input data makes it possible to fit a larger number of batches in memory during training. Moreover, in the case of sparse measurements,training is more efficient computationally. We demonstrate that, in unsupervised settings, RandNet performs dictionary learning using compressed data. In supervised settings, we show that RandNet can classify MNIST images with minimal loss in accuracy, despite being trained with random projections of the images that result in a 50 Overall, our results provide a general principled framework for training neural networks using compressed data.

READ FULL TEXT
research
08/30/2015

Dictionary Learning for Blind One Bit Compressed Sensing

This letter proposes a dictionary learning algorithm for blind one bit c...
research
04/05/2015

Efficient Dictionary Learning via Very Sparse Random Projections

Performing signal processing tasks on compressive measurements of data h...
research
07/12/2018

Scalable Convolutional Dictionary Learning with Constrained Recurrent Sparse Auto-encoders

Given a convolutional dictionary underlying a set of observed signals, c...
research
11/01/2018

Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis

A feature learning task involves training models that are capable of inf...
research
04/30/2015

Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?

Three important properties of a classification machinery are: (i) the sy...
research
07/07/2019

Deep Exponential-Family Auto-Encoders

We consider the problem of learning recurring convolutional patterns fro...
research
03/23/2018

Deep Convolutional Compressed Sensing for LiDAR Depth Completion

In this paper we consider the problem of estimating a dense depth map fr...

Please sign up or login with your details

Forgot password? Click here to reset