Learning deep belief networks from non-stationary streams

Authors:
Roberto Calandra;Tapani Raiko;Marc Peter Deisenroth;Federico Montesino Pouzols
Affiliations:
Fachbereich Informatik, Technische Universität Darmstadt, Germany;Department of Information and Computer Science, Aalto University, Finland;Fachbereich Informatik, Technische Universität Darmstadt, Germany;Department of Biosciences, University of Helsinki, Finland
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 7
Cited 0

On demand classification of data streams

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
A fast learning algorithm for deep belief nets

Neural Computation
Online classification of nonstationary data streams

Intelligent Data Analysis
Dataset Shift in Machine Learning

Dataset Shift in Machine Learning
Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams

Proceedings of the 2010 conference on Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams
Evolving Intelligent Systems: Methodology and Applications

Evolving Intelligent Systems: Methodology and Applications
Learning deep generative models

Learning deep generative models

Quantified Score

Hi-index	0.00

Visualization

Abstract

Deep learning has proven to be beneficial for complex tasks such as classifying images. However, this approach has been mostly applied to static datasets. The analysis of non-stationary (e.g., concept drift) streams of data involves specific issues connected with the temporal and changing nature of the data. In this paper, we propose a proof-of-concept method, called Adaptive Deep Belief Networks, of how deep learning can be generalized to learn online from changing streams of data. We do so by exploiting the generative properties of the model to incrementally re-train the Deep Belief Network whenever new data are collected. This approach eliminates the need to store past observations and, therefore, requires only constant memory consumption. Hence, our approach can be valuable for life-long learning from non-stationary data streams.