Peter Andreae
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Peter Andreae has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoying Gao
Victoria University of Wellington, Wellington, New Zealand
5 shared publications - Bing Xue
Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science, Victoria University of Wellington, New Zealand
4 shared publications - Mengjie Zhang
Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science, Victoria University of Wellington, New Zealand
4 shared publications - Bach Hoai Nguyen
Centre of Data Science and Artificial Intelligence and School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand
3 shared publications - Trevor Londt
Victoria University of Wellington
3 shared publications - Cao Truong Tran
Le Quy Don Technical University, Hanoi, Vietnam
2 shared publications
Latest Publications
- Open Access
XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks
Convolutional Neural Networks (CNNs) continue to achieve great success in classification tasks as innovative techniques and complex multi-path architecture topologies are introduced. Neural Architecture Search (NAS) aims to automate the design of these complex architectures, reducing the need for costly manual design work by human experts. Cellular Encoding (CE) is an evolutionary computation technique which excels in constructing novel multi-path topologies of varying complexity and has recently been applied with NAS to evolve CNN architectures for various classification tasks. However, existing CE approaches have severe limitations. They are restricted to only one domain, only partially implement the theme of CE, or only focus on the micro-architecture search space. This paper introduces a new CE representation and algorithm capable of evolving novel multi-path CNN architectures of varying depth, width, and complexity for image and text classification tasks. The algorithm explicitly focuses on the macro-architecture search space. Furthermore, by using a surrogate model approach, we show that the algorithm can evolve a performant CNN architecture in less than one GPU day, thereby allowing a sufficient number of experiment runs to be conducted to achieve scientific robustness. Experiment results show that the approach is highly competitive, defeating several state-of-the-art methods, and is generalisable to both the image and text domains.
Open AccessXC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks
Convolutional Neural Networks (CNNs) continue to achieve great success in classification tasks as innovative techniques and complex multi-path architecture topologies are introduced. Neural Architecture Search (NAS) aims to automate the design of these complex architectures, reducing the need for costly manual design work by human experts. Cellular Encoding (CE) is an evolutionary computation technique which excels in constructing novel multi-path topologies of varying complexity and has recently been applied with NAS to evolve CNN architectures for various classification tasks. However, existing CE approaches have severe limitations. They are restricted to only one domain, only partially implement the theme of CE, or only focus on the micro-architecture search space. This paper introduces a new CE representation and algorithm capable of evolving novel multi-path CNN architectures of varying depth, width, and complexity for image and text classification tasks. The algorithm explicitly focuses on the macro-architecture search space. Furthermore, by using a surrogate model approach, we show that the algorithm can evolve a performant CNN architecture in less than one GPU day, thereby allowing a sufficient number of experiment runs to be conducted to achieve scientific robustness. Experiment results show that the approach is highly competitive, defeating several state-of-the-art methods, and is generalisable to both the image and text domains.
- 27 November 2023
- Published by Springer Nature
- p. 416-428
XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks
- 27 November 2023
- Published by Springer Nature
- p. 416-428
XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks
- 3 December 2022
- Published by Springer Nature
- p. 646-660
Operation-based Greedy Algorithm for Discounted Knapsack Problem
- 3 December 2022
- Published by Springer Nature
- p. 646-660
Operation-based Greedy Algorithm for Discounted Knapsack Problem
- 1 April 2021
- Published by Springer Nature
- p. 665-680
Evolving Character-Level DenseNet Architectures Using Genetic Programming
- 1 April 2021
- Published by Springer Nature
- p. 665-680
Evolving Character-Level DenseNet Architectures Using Genetic Programming
- 20 November 2019
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 53 (6) , 3849-3899
Semantic association computation: a comprehensive survey
- 20 November 2019
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 53 (6) , 3849-3899
Semantic association computation: a comprehensive survey
- Open Access
- 31 March 2019
- Published by World Scientific Pub Co Pte Ltd in Journal of Innovative Optical Health Sciences
- Vol. 12 (02)
Real-time co-registered photoacoustic and ultrasonic imaging for early endometrial cancer detection driven by cylindrical diffuser
In illuminating tissues, a cylindrical diffuser (CD) has an advantage over regular laser sources due to its ability to illuminate a larger volume of the target tissue. This paper presents a co-registered large volume photoacoustic (PA) and ultrasonic (US) imaging for early endometrial cancer (EEC) detection using CD. It has the advantage that the US imaging system is outside the body and only the PA excitation device is inside the body, which makes the system more efficient and less invasive for EEC detection. The paper reports on two sets of experiments. The first set produced real-time PA images of blood vessel phantom. The second set demonstrated the imaging of pig uterus ex vivo. The results show that the system has the potential for imaging and characterizing of EEC.
- 31 March 2019
- Published by World Scientific Pub Co Pte Ltd in Journal of Innovative Optical Health Sciences
- Vol. 12 (02)
Open AccessReal-time co-registered photoacoustic and ultrasonic imaging for early endometrial cancer detection driven by cylindrical diffuser
In illuminating tissues, a cylindrical diffuser (CD) has an advantage over regular laser sources due to its ability to illuminate a larger volume of the target tissue. This paper presents a co-registered large volume photoacoustic (PA) and ultrasonic (US) imaging for early endometrial cancer (EEC) detection using CD. It has the advantage that the US imaging system is outside the body and only the PA excitation device is inside the body, which makes the system more efficient and less invasive for EEC detection. The paper reports on two sets of experiments. The first set produced real-time PA images of blood vessel phantom. The second set demonstrated the imaging of pig uterus ex vivo. The results show that the system has the potential for imaging and characterizing of EEC.
- 28 March 2016
- Published by Springer Nature in Soft Computing
- Vol. 20 (10) , 3927-3946
New mechanism for archive maintenance in PSO-based multi-objective feature selection
- 28 March 2016
- Published by Springer Nature in Soft Computing
- Vol. 20 (10) , 3927-3946
New mechanism for archive maintenance in PSO-based multi-objective feature selection
- 24 March 2016
- Published by Springer Nature
- p. 149-163
A Genetic Programming-Based Imputation Method for Classification with Missing Data
- 24 March 2016
- Published by Springer Nature
- p. 149-163
A Genetic Programming-Based Imputation Method for Classification with Missing Data
- 15 March 2016
- Published by Springer Nature
- p. 719-736
Mutual Information Estimation for Filter Based Feature Selection Using Particle Swarm Optimization
- 15 March 2016
- Published by Springer Nature
- p. 719-736
Mutual Information Estimation for Filter Based Feature Selection Using Particle Swarm Optimization
- 15 March 2016
- Published by Springer Nature
- p. 685-700
A Wrapper Feature Selection Approach to Classification with Missing Data
- 15 March 2016
- Published by Springer Nature
- p. 685-700
A Wrapper Feature Selection Approach to Classification with Missing Data