Konstantinos N. Plataniotis
6 papers in the PaperMetrix corpus
Papers by this author
-
Discriminative Pattern Mining for Breast Cancer Histopathology Image Classification via Fully Convolutional Autoencoder
2019 · IEEE Access
Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as a variety of benign breast tissue proliferative lesions. In this paper, we propose a …
-
Stain Style Transfer of Histopathology Images Via Structure-Preserved Generative Learning
2020 · arXiv (Cornell University)
Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers. While pathologists do not struggle with color variations in slides, computational solutions usually suffer from …
-
Energy-based Surprise Minimization for Multi-Agent Value Factorization
2020 · arXiv (Cornell University)
Multi-Agent Reinforcement Learning (MARL) has demonstrated significant success in training decentralised policies in a centralised manner by making use of value factorization methods. However, addressing surprise across spurious states and approximation bias remain open problems …
-
On the philosophical, cognitive and mathematical foundations of symbiotic autonomous systems
2021 · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences
Symbiotic autonomous systems (SAS) are advanced intelligent and cognitive systems that exhibit autonomous collective intelligence enabled by coherent symbiosis of human-machine interactions in hybrid societies. Basic research in the emerging field of SAS has triggered …
-
Perspectives on the Emerging Field of Autonomous Systems and its Theoretical Foundations
2021
Autonomous systems are advanced intelligent systems and general AI technologies triggered by the transdisciplinary development in intelligence science, system science, brain science, cognitive science, robotics, computational intelligence, and intelligent mathematics. AS are driven by the …
-
Towards Robust and Automatic Hyper-Parameter Tunning
2021 · ArXiv.org
The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters simultaneously. In this work, we introduce a new class of …