Pub Date : 2020-03-30DOI: 10.1109/ISSC49989.2020.9180185
Ifeatu Ezenwe, Alok Joshi, KongFatt Wong-Lin
Neural networks are complex algorithms that loosely model the behaviour of the human brain. They play a significant role in computational neuroscience and artificial intelligence. The next generation of neural network models is based on the spike timing activity of neurons: spiking neural networks (SNNs). However, model parameters in SNNs are difficult to search and optimise. Previous studies using genetic algorithm (GA) optimisation of SNNs were focused mainly on simple, feedforward, or oscillatory networks, but not much work has been done on optimising cortex-like recurrent SNNs. In this work, we investigated the use of GAs to search for optimal parameters in recurrent SNNs to reach targeted neuronal population firing rates, e.g. as in experimental observations. We considered a cortical column based SNN comprising 1000 Izhikevich spiking neurons for computational efficiency and biologically realism. The model parameters explored were the neuronal biased input currents. First, we found for this particular SNN, the optimal parameter values for targeted population averaged firing activities, and the convergence of algorithm by ~100 generations. We then showed that the GA optimal population size was within ~16-20 while the crossover rate that returned the best fitness value was ~0.95. Overall, we have successfully demonstrated the feasibility of implementing GA to optimize model parameters in a recurrent cortical based SNN.
{"title":"Genetic Algorithmic Parameter Optimisation of a Recurrent Spiking Neural Network Model","authors":"Ifeatu Ezenwe, Alok Joshi, KongFatt Wong-Lin","doi":"10.1109/ISSC49989.2020.9180185","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180185","url":null,"abstract":"Neural networks are complex algorithms that loosely model the behaviour of the human brain. They play a significant role in computational neuroscience and artificial intelligence. The next generation of neural network models is based on the spike timing activity of neurons: spiking neural networks (SNNs). However, model parameters in SNNs are difficult to search and optimise. Previous studies using genetic algorithm (GA) optimisation of SNNs were focused mainly on simple, feedforward, or oscillatory networks, but not much work has been done on optimising cortex-like recurrent SNNs. In this work, we investigated the use of GAs to search for optimal parameters in recurrent SNNs to reach targeted neuronal population firing rates, e.g. as in experimental observations. We considered a cortical column based SNN comprising 1000 Izhikevich spiking neurons for computational efficiency and biologically realism. The model parameters explored were the neuronal biased input currents. First, we found for this particular SNN, the optimal parameter values for targeted population averaged firing activities, and the convergence of algorithm by ~100 generations. We then showed that the GA optimal population size was within ~16-20 while the crossover rate that returned the best fitness value was ~0.95. Overall, we have successfully demonstrated the feasibility of implementing GA to optimize model parameters in a recurrent cortical based SNN.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124486578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-24DOI: 10.1109/ISSC49989.2020.9180189
Viktor Varkarakis, S. Bazrafkan, P. Corcoran
StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper we recap the StyleGAN architecture and training methodology and present our experiences of retraining it on a number of alternative public datasets. Practical issues and challenges arising from the retraining process are discussed. Tests and validation results are presented and a comparative analysis of several different re-trained StyleGAN weightings is provided. The role of this tool in building large, scalable datasets of synthetic facial data is also discussed.
{"title":"Re-Training StyleGAN - A First Step Towards Building Large, Scalable Synthetic Facial Datasets","authors":"Viktor Varkarakis, S. Bazrafkan, P. Corcoran","doi":"10.1109/ISSC49989.2020.9180189","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180189","url":null,"abstract":"StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper we recap the StyleGAN architecture and training methodology and present our experiences of retraining it on a number of alternative public datasets. Practical issues and challenges arising from the retraining process are discussed. Tests and validation results are presented and a comparative analysis of several different re-trained StyleGAN weightings is provided. The role of this tool in building large, scalable datasets of synthetic facial data is also discussed.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125129211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-03-13DOI: 10.1109/ISSC49989.2020.9180166
Faisal Khan, Shubhajit Basak, Hossein Javidnia, M. Schukat, P. Corcoran
In this paper, we explore how synthetically generated 3D face models can be used to construct a high-accuracy ground truth for depth. This allows us to train the Convolutional Neural Networks (CNN) to solve facial depth estimation problems. These models provide sophisticated controls over image variations including pose, illumination, facial expressions and camera position. 2D training samples can be rendered from these models, typically in RGB format, together with depth information. Using synthetic facial animations, a dynamic facial expression or facial action data can be rendered for a sequence of image frames together with ground truth depth and additional metadata such as head pose, light direction, etc. The synthetic data is used to train a CNN-based facial depth estimation system which is validated on both synthetic and real images. Potential fields of application include 3D reconstruction, driver monitoring systems, robotic vision systems, and advanced scene understanding.
{"title":"High-Accuracy Facial Depth Models derived from 3D Synthetic Data","authors":"Faisal Khan, Shubhajit Basak, Hossein Javidnia, M. Schukat, P. Corcoran","doi":"10.1109/ISSC49989.2020.9180166","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180166","url":null,"abstract":"In this paper, we explore how synthetically generated 3D face models can be used to construct a high-accuracy ground truth for depth. This allows us to train the Convolutional Neural Networks (CNN) to solve facial depth estimation problems. These models provide sophisticated controls over image variations including pose, illumination, facial expressions and camera position. 2D training samples can be rendered from these models, typically in RGB format, together with depth information. Using synthetic facial animations, a dynamic facial expression or facial action data can be rendered for a sequence of image frames together with ground truth depth and additional metadata such as head pose, light direction, etc. The synthetic data is used to train a CNN-based facial depth estimation system which is validated on both synthetic and real images. Potential fields of application include 3D reconstruction, driver monitoring systems, robotic vision systems, and advanced scene understanding.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124629590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/3dtv.2013.6676630
J. Watson
I am delighted that its first visit of the 3DTV-CON to the United Kingdom is to the city of Aberdeen, Scotland, the heart of Europe's oil and gas industry. 3D technologies are beginning to play a crucial role in the Energy industry, both in its traditional oil and gas activities, and in the blossoming renewable Energy sector.
{"title":"Chairs Address","authors":"J. Watson","doi":"10.1109/3dtv.2013.6676630","DOIUrl":"https://doi.org/10.1109/3dtv.2013.6676630","url":null,"abstract":"I am delighted that its first visit of the 3DTV-CON to the United Kingdom is to the city of Aberdeen, Scotland, the heart of Europe's oil and gas industry. 3D technologies are beginning to play a crucial role in the Energy industry, both in its traditional oil and gas activities, and in the blossoming renewable Energy sector.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115952803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：