ΕΛ EN
Home | People | Kalais, Konstantinos
3
Scholarly Works
33%
OA Ratio
0%
Collaborative Ratio
Scholar

Kalais, Konstantinos

0
H-index (Google Scholar)
-
Scholar Citations

Scholarly Works

Research Output

Recent Publications

Stochastic Deep Networks with Linear Competing Units for Transfer Learning

Chatzis, Sotirios P., Kalais, Konstantinos
Publishing year: 2024
Thesis Repository
Deep Learning (DL) has become the preferred approach to addressing various challenging machine learning (MLe) tasks, like computer vision, natural language processing, and speech recognition. Deep Neural Networks (DNN's) have achieved superior performance in those tasks compared to traditional MLe methods. However, they entail a huge number of weights causing them to make over-confident predictions, that may reduce their generalization capacity in hard problems, e.g. a Meta-Learning (ML) scenario. To mitigate this issue, researchers have applied Bayesian modeling to DNN's, where they employ Bayesian Neural Networks (BNN's) with more robust and tractable estimates of uncertainty in a model's predictions. That way, we can build safer MLe systems in safety-critical applications, such as healthcare, video recognition, and autonomous vehicle control. DL models trained to solve a single task suffer from a common drawback: they cannot combine data from diverse tasks in order to learn new tasks in a future training round. Such models often require extensive training and data collection for each task individually, which can be time-consuming and data-intensive. This limitation has given rise to the importance of research in ML. This field aims to address these shortcomings by developing methods that allow existing models to efficiently learn from and adapt quickly to new tasks, by leveraging knowledge gained from previous tasks. Therefore, ML methods aim to make models more capable...

Cybersecurity training and healthcare: the AERAS approach

Damiani, Ernesto, Darau, Georgiana, Floros, Evangelos, Frati, Fulvio, Iordanou, Costas, Kagadis, George C., Kalais, Konstantinos, Leonidou, Pantelitsa, Najar, Jihane, Nikitakis, George, Plachouris, Dimitris, Salamanos, N...
Publishing year: 2024
Journal article
International Journal of Information Security, 2024, Volume 23, Issue 2
Repository
Cyber ranges have gained significant importance in cybersecurity training in recent years, and they are still playing a role of paramount importance, thanks to their ability to give trainees hands-on experience with real-world exercises. This paper presents the motivation and objective of the AERAS project, including a thorough analysis of data from ad hoc interviews and surveys specifically designed and administered for the project’s goals. AERAS aims to apply the cyber range concept to the critical healthcare sector. The AERAS platform will be a virtual cyberwarfare solution that will simulate the operation and effects of security controls and offer hands-on training on their development, assessment, use, and management.

Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning

Chatzis, Sotirios P., Kalais, Konstantinos
Publishing year: 2022
Conference paper
International Conference on Machine Learning, 2022
Repository
Pages 10586-10597
This work addresses meta-learning (ML) by considering deep networks with stochastic local winner-takes-all (LWTA) activations. This type of network units results in sparse representations from each model layer, as the units are organized into blocks where only one unit generates a non-zero output. The main operating principle of the introduced units rely on stochastic principles, as the network performs posterior sampling over competing units to select the winner. Therefore, the proposed networks are explicitly designed to extract input data representations of sparse stochastic nature, as opposed to the currently standard deterministic representation paradigm. Our approach produces state-of-the-art predictive accuracy on few-shot image classification and regression experiments, as well as reduced predictive error on an active learning setting; these improvements come with an immensely reduced computational cost. Code is available at: https://github.com/Kkalais/StochLWTA-ML

3
Unique publications
33.3%
Open access (1 publications; 2 without information)
0%
With other institutions (0 publications; 3 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 0 0 0
H5-index 0 0 0
H10-index 0 0 0

Publications per year and source

No description yet.