113 citations · 504 across the 39 of their papers we have counts for
22 papers · 1 filter
Class-Incremental Learning via Knowledge Amalgamation
Marcus de Carvalho, Mahardhika Pratama, Jie Zhang +1
Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting. Numerous methods have been proposed t…
Scalable Adversarial Online Continual Learning
Tanmoy Dam, Mahardhika Pratama, MD Meftahul Ferdaus +2
Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susce…
Reinforced Continual Learning for Graphs
Appan Rakaraddi, Siew Kei Lam, Mahardhika Pratama +1
Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs and similar topological data structures. While many works have been established in…
Latent Preserving Generative Adversarial Network for Imbalance classification
Tanmoy Dam, Md Meftahul Ferdaus, Mahardhika Pratama +3
Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic classification algorithms tend…
Autonomous Cross Domain Adaptation under Extreme Label Scarcity
Weiwei Weng, Mahardhika Pratama, Choiru Za'in +4
A cross domain multistream classification is a challenging problem calling for fast domain adaptations to handle different but related streams in never-ending and rapidly changing…
ACDC: Online Unsupervised Cross-Domain Adaptation
Marcus de Carvalho, Mahardhika Pratama, Jie Zhang +1
We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source strea…
Unsupervised Continual Learning in Streaming Environments
Andri Ashfahani, Mahardhika Pratama
A deep clustering network is desired for data streams because of its aptitude in extracting natural features thus bypassing the laborious feature engineering step. While automatic…
Automatic Online Multi-Source Domain Adaptation
Renchunzi Xie, Mahardhika Pratama
Knowledge transfer across several streaming processes remain challenging problem not only because of different distributions of each stream but also because of rapidly changing and…
Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approach
Mahardhika Pratama, Andri Ashfahani, Edwin Lughofer
Unsupervised continual learning remains a relatively uncharted territory in the existing literature because the vast majority of existing works call for unlimited access of ground…
Autonomous Deep Quality Monitoring in Streaming Environments
Andri Ashfahani, Mahardhika Pratama, Edwin Lughofer +1
The common practice of quality monitoring in industry relies on manual inspection well-known to be slow, error-prone and operator-dependent. This issue raises strong demand for aut…
Continual Learning via Inter-Task Synaptic Mapping
Mao Fubing, Weng Weiwei, Mahardhika Pratama +1
Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC hav…
Weakly Supervised Deep Learning Approach in Streaming Environments
Mahardhika Pratama, Andri Ashfahani, Mohamad Abdul Hady
The feasibility of existing data stream algorithms is often hindered by the weakly supervised condition of data streams. A self-evolving deep neural network, namely Parsimonious Ne…
ATL: Autonomous Knowledge Transfer from Many Streaming Processes
Mahardhika Pratama, Marcus de Carvalho, Renchunzi Xie +2
Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the ta…
DEVDAN: Deep Evolving Denoising Autoencoder
Andri Ashfahani, Mahardhika Pratama, Edwin Lughofer +1
The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic des…
Automatic Construction of Multi-layer Perceptron Network from Streaming Examples
Mahardhika Pratama, Choiru Za'in, Andri Ashfahani +2
Autonomous construction of deep neural network (DNNs) is desired for data streams because it potentially offers two advantages: proper model's capacity and quick reaction to drift…
Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments
Andri Ashfahani, Mahardhika Pratama
The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning…
Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams
Mahardhika Pratama, Andri Ashfahani, Yew Soon Ong +2
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. None…
Deep Stacked Stochastic Configuration Networks for Lifelong Learning of Non-Stationary Data Streams
Mahardhika Pratama, Dianhui Wang
The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enable…
Online Tool Condition Monitoring Based on Parsimonious Ensemble+
Mahardhika Pratama, Eric Dimla, Edwin Lughofer +2
Accurate diagnosis of tool wear in metal turning process remains an open challenge for both scientists and industrial practitioners because of inhomogeneities in workpiece material…
Evolving Ensemble Fuzzy Classifier
Mahardhika Pratama, Witold Pedrycz, Edwin Lughofer
The concept of ensemble learning offers a promising avenue in learning from data streams under complex environments because it addresses the bias and variance dilemma better than i…
A novel online multi-label classifier for high-speed streaming data applications
Rajasekar Venkatesan, Meng Joo Er, Mihika Dave +2
In this paper, a high-speed online neural network classifier based on extreme learning machines for multi-label classification is proposed. In multi-label classification, each of t…
A Novel Online Real-time Classifier for Multi-label Data Streams
Rajasekar Venkatesan, Meng Joo Er, Shiqian Wu +1
In this paper, a novel extreme learning machine based online multi-label classifier for real-time data streams is proposed. Multi-label classification is one of the actively resear…