Incremental learning algorithms and applications
A Gepperth, B Hammer - European symposium on artificial neural …, 2016 - hal.science
Incremental learning refers to learning from streaming data, which arrive over time, with
limited memory resources and, ideally, without sacrificing model accuracy. This setting fits …
limited memory resources and, ideally, without sacrificing model accuracy. This setting fits …
A bio-inspired incremental learning architecture for applied perceptual problems
A Gepperth, C Karaoguz - Cognitive Computation, 2016 - Springer
We present a biologically inspired architecture for incremental learning that remains
resource-efficient even in the face of very high data dimensionalities (> 1000) that are …
resource-efficient even in the face of very high data dimensionalities (> 1000) that are …
An imbalance modified deep neural network with dynamical incremental learning for chemical fault diagnosis
Z Hu, P Jiang - IEEE Transactions on Industrial Electronics, 2018 - ieeexplore.ieee.org
In this paper, a data-driven fault diagnosis model dealing with chemical imbalanced data
streams is investigated. Different faults occur with varied frequencies by continuous arrival in …
streams is investigated. Different faults occur with varied frequencies by continuous arrival in …
Deep learning for malicious flow detection
Cyber security has grown up to be a hot issue in recent years. How to identify potential
malware becomes a challenging task. To tackle this challenge, we adopt deep learning …
malware becomes a challenging task. To tackle this challenge, we adopt deep learning …
A novel semi-supervised ensemble algorithm using a performance-based selection metric to non-stationary data streams
In this article, we consider the semi-supervised data stream classification problems. Most of
the semi-supervised learning algorithms suffer from a proper selection metric to select from …
the semi-supervised learning algorithms suffer from a proper selection metric to select from …
Locality-based transfer learning on compression autoencoder for efficient scientific data lossy compression
Scientific simulation can generate petabyte-level data per run nowadays. To significantly
reduce the data size while simultaneously maintaining the compression quality based on …
reduce the data size while simultaneously maintaining the compression quality based on …
[HTML][HTML] STDS: self-training data streams for mining limited labeled data in non-stationary environment
Inthis article, wefocus on the classification problem to semi-supervised learning in non-
stationary environment. Semi-supervised learning is a learning task from both labeled and …
stationary environment. Semi-supervised learning is a learning task from both labeled and …
Logistic regression learning model for handling concept drift with unbalanced data in credit card fraud detection system
P Kulkarni, R Ade - Proceedings of the Second International Conference …, 2016 - Springer
Credit card is the well-accepted manner of remission in financial field. With the rising
number of users across the globe, risks on usage of credit card have also been increased …
number of users across the globe, risks on usage of credit card have also been increased …
[HTML][HTML] Parameter estimation in abruptly changing dynamic environments using stochastic learning weak estimator
Many real-life dynamical systems experience abrupt changes followed by almost stationary
periods. In this paper, we consider streams of data exhibiting such abrupt behavior and …
periods. In this paper, we consider streams of data exhibiting such abrupt behavior and …
Incremental learning with self-organizing maps
A Gepperth, C Karaoguz - 2017 12th International Workshop …, 2017 - ieeexplore.ieee.org
We present a novel use for self-organizing maps (SOMs) as an essential building block for
incremental learning algorithms. SOMs are very well suited for this purpose because they …
incremental learning algorithms. SOMs are very well suited for this purpose because they …