Y
Yani Ioannou
Researcher at University of Cambridge
Publications - 30
Citations - 1817
Yani Ioannou is an academic researcher from University of Cambridge. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 17, co-authored 26 publications receiving 1495 citations. Previous affiliations of Yani Ioannou include Google & Toronto Rehabilitation Institute.
Papers
More filters
Posted Content
Measuring Neural Net Robustness with Constraints
Osbert Bastani,Yani Ioannou,Leonidas Lampropoulos,Dimitrios Vytiniotis,Aditya V. Nori,Antonio Criminisi +5 more
TL;DR: In this paper, the authors propose metrics for measuring the robustness of a neural network and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program.
Segmentation of Brain Tumor Tissues with Convolutional Neural Networks
TL;DR: In this paper, the authors apply CNNs to segmentation of brain tumor tissues, using multi-channel intensity information from a small patch around each point to be labeled, and only standard intensity pre-processing is applied to the input data to account for scanner differences.
Proceedings ArticleDOI
Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
TL;DR: In this article, a sparse connection structure that resembles a tree root was proposed to reduce the number of parameters and computational cost of deep CNNs, without compromising accuracy, by exploiting the sparsity of inter-layer filter dependencies.
Proceedings ArticleDOI
Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
TL;DR: In this paper, a sparse connection structure that resembles a tree root was proposed to reduce the number of parameters and the computational cost of deep CNNs without compromising the accuracy, exploiting the sparsity of inter-layer filter dependencies.
Proceedings ArticleDOI
Difference of Normals as a Multi-scale Operator in Unorganized Point Clouds
TL;DR: The Difference of Normals (DoN) provides a computationally efficient, multi-scale approach to processing large unorganized 3D point clouds and is shown to segment large 3Dpoint clouds into scale-salient clusters towards applications in semi-automatic annotation, and as a pre-processing step in automatic object recognition.