Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders

By Alexander Ororbia, C. Lee Giles, David Reitter. 2015

30 citations recorded by the source corpus.

Two novel deep hybrid architectures, the Deep Hybrid Boltzmann Machine and the Deep Hybrid Denoising Auto-encoder, are proposed for handling semi-supervised learning problems. The models combine experts that model relevant distributions at different levels of abstraction to improve overall predictive performance on discriminative tasks. Theoretical motivations and algorithms for joint learning for each are presented. We apply the new models to the domain of data-streams in work towards life-long learning. The proposed architectures show improved performance compared to a pseudo-labeled, drop-out rectifier network.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Eric Eaton
2. Decebal Constantin Mocanu
3. Antonio Liotta
4. Maria Torres Vega
5. Peter Stone
6. Matthew E. Taylor
7. Mohammad Rostami
8. Sergey Levine

In Computer Vision and Pattern Recognition

1. Decebal Constantin Mocanu
2. Antonio Liotta
3. Eric Eaton
4. Peter Stone
5. Maria Torres Vega
6. Todd Hester
7. Faraz Torabi

In Signal Processing

1. Eric Eaton
2. Peter Stone
3. Antonio Liotta
4. Decebal Constantin Mocanu

Citations in the corpus

• Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data (2016, methodology): “Ororbia et al (2015) proposed an online semi-supervised learning algorithm using deep hybrid Boltzmann machines and denoising autoencoders.”