no code implementations • 26 Mar 2024 • Xiao-Cheng Liao, Yi Mei, Mengjie Zhang
In our approach, we design a concept of phase urgency for each signal phase.
1 code implementation • 1 Mar 2024 • Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang
In this paper, we develop upon the topic of loss function learning, an emergent meta-learning paradigm that aims to learn loss functions that significantly improve the performance of the models trained under them.
no code implementations • 1 Feb 2024 • Su Nguyen, Dhananjay Thiruvady, Yuan Sun, Mengjie Zhang
In the proposed algorithm, evolved programs represent variable selectors to be used in the search process of constraint programming, and their fitness is determined by the quality of solutions obtained for training instances.
no code implementations • 1 Feb 2024 • Kaan Demir, Bach Nguyen, Bing Xue, Mengjie Zhang
The consistency of surrogate loss functions is not proven and is exacerbated by the conflicting nature of multi-label loss functions.
no code implementations • 18 Aug 2023 • Carl McMillan, Junhong Zhao, Bing Xue, Ross Vennell, Mengjie Zhang
To establish an effective deep learning model for buoy detection with a limited number of labeled data, we employ transfer learning techniques.
no code implementations • 18 Apr 2023 • Peng Zeng, Xiaotian Song, Andrew Lensen, Yuwei Ou, Yanan sun, Mengjie Zhang, Jiancheng Lv
With these designs, the proposed DGP method can efficiently search for the GP trees with higher performance, thus being capable of dealing with high-dimensional SR. To demonstrate the effectiveness of DGP, we conducted various experiments against the state of the arts based on both GP and deep neural networks.
1 code implementation • IEEE Transactions on Evolutionary Computation 2023 • Hengzhe Zhang, Aimin Zhou, Qi Chen, Bing Xue, Mengjie Zhang
Ensemble learning methods have been widely used in machine learning in recent years due to their high predictive performance.
no code implementations • 30 Jan 2023 • Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang
Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model.
no code implementations • 7 Dec 2022 • Bin Wang, Bing Xue, Mengjie Zhang
In this paper, inspired by transfer learning, a new evolutionary computation based framework is proposed to efficiently evolve CNNs without compromising the classification accuracy.
no code implementations • 28 Nov 2022 • Bin Wang, Wenbin Pei, Bing Xue, Mengjie Zhang
The evolved local explanations on four images, randomly selected from ImageNet, are presented, which show that the evolved local explanations are straightforward to be recognised by humans.
no code implementations • 27 Sep 2022 • Ying Bi, Bing Xue, Mengjie Zhang
The new approach can automatically evolve variable-length models using many important operators from both image and classification domains.
no code implementations • 19 Sep 2022 • Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang
In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them.
no code implementations • 14 Sep 2022 • Ying Bi, Bing Xue, Pablo Mesejo, Stefano Cagnoni, Mengjie Zhang
This survey aims to provide a better understanding of evolutionary computer vision (ECV) by discussing the contributions of different approaches and exploring how and why EC is used for CV and image analysis.
no code implementations • 23 Aug 2022 • Nan Li, Lianbo Ma, Guo Yu, Bing Xue, Mengjie Zhang, Yaochu Jin
Specifically, we firstly illuminate EDL from machine learning and EC and regard EDL as an optimization problem.
no code implementations • 3 Jul 2022 • Xiangning Xie, Yuqiao Liu, Yanan sun, Mengjie Zhang, Kay Chen Tan
Performance predictors can greatly alleviate the prohibitive cost of NAS by directly predicting the performance of DNNs.
no code implementations • 13 Apr 2022 • Ranju Mandal, Basim Azam, Brijesh Verma, Mengjie Zhang
The empirical analysis reveals that optimized visual features with global and local contextual information play a significant role to improve accuracy and produce stable predictions comparable to state-of-the-art deep CNN models.
no code implementations • 23 Aug 2021 • Andrew Lensen, Bing Xue, Mengjie Zhang
Recently, genetic programming has emerged as a very promising approach to manifold learning by evolving functional mappings from the original space to an embedding.
1 code implementation • 9 Aug 2021 • Xiangning Xie, Yuqiao Liu, Yanan sun, Gary G. Yen, Bing Xue, Mengjie Zhang
The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform.
no code implementations • 17 Dec 2020 • Ying Bi, Bing Xue, Mengjie Zhang
Therefore, this paper develops a multitask GP approach to image feature learning for classification with limited training data.
no code implementations • 25 Aug 2020 • Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang, Gary G. Yen, Kay Chen Tan
Deep Neural Networks (DNNs) have achieved great success in many applications.
no code implementations • 15 Aug 2020 • Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang
Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks.
no code implementations • 3 Jul 2020 • Bin Wang, Bing Xue, Mengjie Zhang
A new effective and efficient surrogate-assisted particle swarm optimisation algorithm is proposed to automatically evolve convolutional neural networks.
no code implementations • 2 Jun 2020 • Isidro M. Alvarez, Trung B. Nguyen, Will N. Browne, Mengjie Zhang
However, this method was unrefined and suited to only the Multiplexer problem domain.
no code implementations • 8 May 2020 • Trung B. Nguyen, Will N. Browne, Mengjie Zhang
This paper seeks to facilitate the automation of feature transferring in between tasks by utilising the observed list.
no code implementations • 23 Apr 2020 • Trung B. Nguyen, Will N. Browne, Mengjie Zhang
This paper aims to optimise the structural efficiency of CFs in XOF.
no code implementations • 16 Feb 2020 • Yanan Sun, Ziyao Ren, Gary G. Yen, Bing Xue, Mengjie Zhang, Jiancheng Lv
Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs.
1 code implementation • 28 Jan 2020 • Benjamin Patrick Evans, Bing Xue, Mengjie Zhang
We apply this to the area of automated machine learning (by extending TPOT), to produce pipelines which can effectively be claimed to be free from human input, and show that the results are competitive with existing state-of-the-art which use hand-selected hyperparameter values.
1 code implementation • 27 Jan 2020 • Andrew Lensen, Bing Xue, Mengjie Zhang
Many domains require an understanding of the data in terms of the original features; there is hence a need for powerful visualisation methods which use understandable models.
no code implementations • 23 Jan 2020 • Benjamin Patrick Evans, Bing Xue, Mengjie Zhang
A common problem machine learning developers are faced with is overfitting, that is, fitting a pipeline too closely to the training data that the performance degrades for unseen data.
no code implementations • 5 Jan 2020 • Andrew Lensen, Mengjie Zhang, Bing Xue
This method required the dimensionality of the embedding to be known a priori, which makes it hard to use when little is known about a dataset.
no code implementations • 20 Nov 2019 • Jordan MacLachlan, Yi Mei, Juergen Branke, Mengjie Zhang
Due to its direct relevance to post-disaster operations, meter reading and civil refuse collection, the Uncertain Capacitated Arc Routing Problem (UCARP) is an important optimisation problem.
no code implementations • 22 Oct 2019 • Andrew Lensen, Bing Xue, Mengjie Zhang
In this paper, we propose a new approach to automatically evolving similarity functions for a given clustering algorithm by using genetic programming.
1 code implementation • 28 Sep 2019 • Benjamin Patrick Evans, Harith Al-Sahaf, Bing Xue, Mengjie Zhang
Image classification is an essential task in computer vision, which aims to categorise a set of images into different groups based on some visual criteria.
no code implementations • 12 Aug 2019 • Samaneh Azari, Bing Xue, Mengjie Zhang, Lifeng Peng
The GP method along with RF and SVR, each is used for post-processing the results of peptide identification by PEAKS, a commonly used de novo sequencing method.
no code implementations • 29 Jul 2019 • Bin Wang, Bing Xue, Mengjie Zhang
Deep Convolutional Neural Networks (CNNs) have been widely used in image classification tasks, but the process of designing CNN architectures is very complex, so Neural Architecture Search (NAS), automatically searching for optimal CNN architectures, has attracted more and more research interests.
1 code implementation • GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference 2019 • Ying Bi, Bing Xue, Mengjie Zhang
An ensemble consists of multiple learners and can achieve a better generalisation performance than a single learner.
1 code implementation • 21 Mar 2019 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
In recent years, convolutional neural networks (CNNs) have become deeper in order to achieve better classification accuracy in image classification.
no code implementations • 10 Mar 2019 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs.
no code implementations • 8 Feb 2019 • Andrew Lensen, Bing Xue, Mengjie Zhang
Exploratory data analysis is a fundamental aspect of knowledge discovery that aims to find the main characteristics of a dataset.
no code implementations • 28 Oct 2018 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
The proposed algorithm is evaluated on CIFAR10 and CIFAR100 against 18 state-of-the-art peer competitors.
no code implementations • 2 Sep 2018 • Gang Chen, Yiming Peng, Mengjie Zhang
With the aim of improving sample efficiency and learning performance, we will develop a new DRL algorithm in this paper that seamless integrates entropy-induced and bootstrap-induced techniques for efficient and deep exploration of the learning environment.
no code implementations • 20 Aug 2018 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN.
4 code implementations • 11 Aug 2018 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years.
no code implementations • 17 Apr 2018 • Gang Chen, Yiming Peng, Mengjie Zhang
While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves data efficiency by performing multiple epochs of \emph{clipped policy optimization} from sampled data.
no code implementations • 17 Mar 2018 • Bin Wang, Yanan sun, Bing Xue, Mengjie Zhang
Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.
no code implementations • 2 Feb 2018 • Andrew Lensen, Bing Xue, Mengjie Zhang
Recently, feature selection has become an increasingly important area of research due to the surge in high-dimensional datasets in all areas of modern life.
1 code implementation • 13 Dec 2017 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years.
1 code implementation • 30 Oct 2017 • Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights.
2 code implementations • 12 Jul 2016 • Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, Wen Li
In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition.
no code implementations • 15 Oct 2015 • Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn, Mengjie Zhang
We propose Scatter Component Analyis (SCA), a fast representation learning algorithm that can be applied to both domain adaptation and domain generalization.
Ranked #7 on Domain Adaptation on Office-Caltech
3 code implementations • ICCV 2015 • Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang, David Balduzzi
The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previously unseen domains.
no code implementations • 21 Sep 2014 • Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang
We propose a simple neural network model to deal with the domain adaptation problem in object recognition.