Antreas Antoniou - Academia.edu (original) (raw)

Uploads

Papers by Antreas Antoniou

IEEE Transactions on Pattern Analysis and Machine Intelligence

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent ... more The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many conventional challenges of deep learning, including data and computation bottlenecks, as well as generalization. This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning. Finally, we discuss outstanding challenges and promising areas for future research.

Artificial Neural Networks and Machine Learning – ICANN 2018

Effective training of neural networks requires much data. In the low-data regime, parameters are ... more Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively, but standard data augmentation produces only limited plausible alternative data. Given the potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, uses data from a source domain and learns to take a data item and augment it by generating other withinclass data items. As this generative process does not depend on the classes themselves, it can be applied to novel unseen classes. We demonstrate that a Data Augmentation Generative Adversarial Network (DA-GAN) augments classifiers well on Omniglot, EMNIST and VGG-Face.

Journal of Applied Physics, 2007

We report on a spectroscopic study of very thin nanocrystalline silicon films varying between 5 a... more We report on a spectroscopic study of very thin nanocrystalline silicon films varying between 5 and 30 nm. The role of quantum confinement effect and surface passivation of nanograins in optical properties are examined in detail. The coupling between surface vibrations and fundamental gap Eg as well as the increase of interaction between them at the strong confinement regime (<=2

2016 International Joint Conference on Neural Networks (IJCNN), 2016

In this paper the design, implementation, and evaluation of a general purpose smartphone based in... more In this paper the design, implementation, and evaluation of a general purpose smartphone based intelligent surveillance system is presented. It has two main elements; i) a detection module, and ii) a classification module. The detection module is based on the recently introduced approach that combines the well-known background subtraction method with the optical flow and recursively estimated density. The classification module is based on a neural network using Deep Learning methodology. Firstly, the architecture design of the convolutional neural network is presented and analyzed in the context of the four selected architectures (two of them recent successful types) and two custom modifications specifically made for the problem at hand. The results are carefully evaluated, and the best one is selected to be used within the proposed system. In addition, the system is implemented on both a PC (using Linux type OS) and on a smartphone (using Android). In addition to the compatibility with all modern Android-based devices, most GPU-powered platforms such as Raspberry Pi, Nvidia Tegra X1 and Jetson run on Linux. The proposed system can easily be installed on any such device benefiting from the advantage of parallelisation for faster execution. The proposed system achieved a performance which surpasses that of a human (classification accuracy of the top 1 class >95.9% for automatic recognition of a detected object into one of the seven selected categories. For the top-2 classes, the accuracy is even higher (99.85%). That means, at least, one of the two top classes suggested by the system is correct. Finally, a number of visual examples are showcased of the system in use in both PC and Android devices.

IEEE Transactions on Pattern Analysis and Machine Intelligence

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent ... more The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many conventional challenges of deep learning, including data and computation bottlenecks, as well as generalization. This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning. Finally, we discuss outstanding challenges and promising areas for future research.

Artificial Neural Networks and Machine Learning – ICANN 2018

Effective training of neural networks requires much data. In the low-data regime, parameters are ... more Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively, but standard data augmentation produces only limited plausible alternative data. Given the potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, uses data from a source domain and learns to take a data item and augment it by generating other withinclass data items. As this generative process does not depend on the classes themselves, it can be applied to novel unseen classes. We demonstrate that a Data Augmentation Generative Adversarial Network (DA-GAN) augments classifiers well on Omniglot, EMNIST and VGG-Face.

Journal of Applied Physics, 2007

We report on a spectroscopic study of very thin nanocrystalline silicon films varying between 5 a... more We report on a spectroscopic study of very thin nanocrystalline silicon films varying between 5 and 30 nm. The role of quantum confinement effect and surface passivation of nanograins in optical properties are examined in detail. The coupling between surface vibrations and fundamental gap Eg as well as the increase of interaction between them at the strong confinement regime (<=2

2016 International Joint Conference on Neural Networks (IJCNN), 2016

In this paper the design, implementation, and evaluation of a general purpose smartphone based in... more In this paper the design, implementation, and evaluation of a general purpose smartphone based intelligent surveillance system is presented. It has two main elements; i) a detection module, and ii) a classification module. The detection module is based on the recently introduced approach that combines the well-known background subtraction method with the optical flow and recursively estimated density. The classification module is based on a neural network using Deep Learning methodology. Firstly, the architecture design of the convolutional neural network is presented and analyzed in the context of the four selected architectures (two of them recent successful types) and two custom modifications specifically made for the problem at hand. The results are carefully evaluated, and the best one is selected to be used within the proposed system. In addition, the system is implemented on both a PC (using Linux type OS) and on a smartphone (using Android). In addition to the compatibility with all modern Android-based devices, most GPU-powered platforms such as Raspberry Pi, Nvidia Tegra X1 and Jetson run on Linux. The proposed system can easily be installed on any such device benefiting from the advantage of parallelisation for faster execution. The proposed system achieved a performance which surpasses that of a human (classification accuracy of the top 1 class >95.9% for automatic recognition of a detected object into one of the seven selected categories. For the top-2 classes, the accuracy is even higher (99.85%). That means, at least, one of the two top classes suggested by the system is correct. Finally, a number of visual examples are showcased of the system in use in both PC and Android devices.