Retinal vessel information is helpful in retinal disease screening and diagnosis. Retinal vessel segmentation provides useful information about vessels and can be used by physicians during intraocular surgery and retinal diagnostic operations. Convolutional neural networks (CNNs) are powerful tools for classification and segmentation of medical images. Complexity of CNNs makes it difficult to i...

Detection of partially occluded objects is a challenging computer vision problem. Standard Convolutional Neural Network (CNN) detectors fail if parts of the detection window are occluded, since not every sub-part of the window is discriminative on its own. To address this issue, we propose a novel loss layer for CNNs, named grid loss, which minimizes the error rate on sub-blocks of a convolutio...

This work investigates how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. Unlike previous work, this study considers networks where each layer may use different precision data. Our key result is the observation that the tolerance of CNNs to reduced precision data not only varies across networks, a well established observation...

Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical explanation and develop a mathematical model of sparse signal recovery that is consistent with CNNs with random weights. We give an exact connection to a par...

I put together these notes as part of my TA work for the Graph and Text Mining grad course of Prof. Michalis Vazirgiannis in the Spring of 2017. They accompanied a programming lab session about Convolutional Neural Networks (CNNs) and Long Short Term Memory networks (LSTMs) for document classification, using Python and Keras1. Keras is a very popular Python library for deep learning. It is a wr...

In this paper we discuss a method for semi-supervised training of CNNs. By using auto-encoders to extract features from unlabeled images, we can train CNNs to accurately classify images with only a small set of labeled images. We show our method’s results on a shallow CNN using the CIFAR-10 dataset, and some preliminary results on a VGG-16 network using the STL-10 dataset.

In this paper a method for synchronizing high dimensional chaotic systems is developed. The objective is to generate a linear error dynamics between the master and the slave systems, so that synchronization is achievable by exploiting the controllability property of linear systems. The suggested approach is applied to Cellular Neural Networks (CNNs), which can be considered as a tool for genera...

Global exponential stability for a class of cellular neural networks (CNNs) with time-varying delay is considered. By using the method of Lyapunov Krasovskii functional and linear matrix inequality (LMI) technique, some sufficient conditions for global exponential stability of CNNs are obtained. The conditions presented here are related to the size of delay. An example is given to illustrate th...

This work explores CNNs for the recognition of novel categories from few examples. Inspired by the transferability analysis of CNNs, we introduce an additional unsupervised meta-training stage that exposes multiple top layer units to a large amount of unlabeled real-world images. By encouraging these units to learn diverse sets of low-density separators across the unlabeled data, we capture a m...

Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks. Their convolutional filters are of paramount importance for they allow to learn patterns while disregarding their locations in input images. When facing highly irregular domains, generalized convolutional operators based on an underlying graph structure have been proposed. However, these o...