SOINN+, a Self-Organizing Incremental Neural Network for Unsupervised Learning from Noisy Data Streams. (1st April 2020)
- Record Type:
- Journal Article
- Title:
- SOINN+, a Self-Organizing Incremental Neural Network for Unsupervised Learning from Noisy Data Streams. (1st April 2020)
- Main Title:
- SOINN+, a Self-Organizing Incremental Neural Network for Unsupervised Learning from Noisy Data Streams
- Authors:
- Wiwatcharakoses, Chayut
Berrar, Daniel - Abstract:
- Highlights: We present a new self-organizing incremental neural network: SOINN+. SOINN+ is for unsupervised, continuous learning. SOINN+ can detect clusters in noisy, evolving data streams. SOINN+ mitigates catastrophic forgetting. Abstract: The goal of continuous learning is to acquire and fine-tune knowledge incrementally without erasing already existing knowledge. How to mitigate this erasure, known as catastrophic forgetting, is a grand challenge for machine learning, specifically when systems are trained on evolving data streams. Self-organizing incremental neural networks (SOINN) are a class of neural networks that are designed for continuous learning from non-stationary data. Here, we propose a novel method, SOINN+, which is fundamentally different from the previous generations of SOINN with respect to how "forgetting" is modeled. To achieve a more graceful forgetting, we developed three new concepts: idle time, trustworthiness, and unutility of a node. SOINN+ learns a topology-preserving mapping of the input data to a network structure, which reveals clusters of arbitrary shapes in streams of noisy data. Our experiments with synthetic and real-world data sets showed that SOINN+ can maintain discovered structures even under sudden and recurring concept drifts.
- Is Part Of:
- Expert systems with applications. Volume 143(2020)
- Journal:
- Expert systems with applications
- Issue:
- Volume 143(2020)
- Issue Display:
- Volume 143, Issue 2020 (2020)
- Year:
- 2020
- Volume:
- 143
- Issue:
- 2020
- Issue Sort Value:
- 2020-0143-2020-0000
- Page Start:
- Page End:
- Publication Date:
- 2020-04-01
- Subjects:
- Continuous learning -- Catastrophic forgetting -- Self-organizing incremental neural network -- Non-stationary data -- Data stream -- Concept drift
Expert systems (Computer science) -- Periodicals
Systèmes experts (Informatique) -- Périodiques
Electronic journals
006.33 - Journal URLs:
- http://www.sciencedirect.com/science/journal/09574174 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.eswa.2019.113069 ↗
- Languages:
- English
- ISSNs:
- 0957-4174
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3842.004220
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 12512.xml