Related papers: Application of Sensitivity Analysis Methods for St…
A convolution model which accounts for neural activity dynamics in the primary visual cortex is derived and used to detect visually salient contours in images. Image inputs to the model are modulated by long-range horizontal connections,…
Road safety mapping using satellite images is a cost-effective but a challenging problem for smart city planning. The scarcity of labeled data, misalignment and ambiguity makes it hard for supervised deep networks to learn efficient…
Computational modeling is becoming a widely used methodology in modern neuroscience. However, as the complexity of the phenomena under study increases, the analysis of the results emerging from the simulations concomitantly becomes more…
We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compressed using a neural network trained in…
Neural network approaches are machine learning methods that are widely used in various domains, such as healthcare and cybersecurity. Neural networks are especially renowned for their ability to deal with image datasets. During the training…
Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly limited owing to their poor scalability with larger networks.…
Human emotion recognition is an active research area in artificial intelligence and has made substantial progress over the past few years. Many recent works mainly focus on facial regions to infer human affection, while the surrounding…
Image super-resolution (SR) techniques have been developing rapidly, benefiting from the invention of deep networks and its successive breakthroughs. However, it is acknowledged that deep learning and deep neural networks are difficult to…
Computational models of the cardiovascular system are increasingly used for the diagnosis, treatment, and prevention of cardiovascular disease. Before being used for translational applications, the predictive abilities of these models need…
The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative…
We consider the problem of estimating parameter sensitivity for Markovian models of reaction networks. Sensitivity values measure the responsiveness of an output to the model parameters. They help in analyzing the network, understanding its…
Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many cases, such as 3D volume or video classification tasks, not…
Learning-based methods especially with convolutional neural networks (CNN) are continuously showing superior performance in computer vision applications, ranging from image classification to restoration. For image classification, most…
We present a method to accelerate global illumination computation in dynamic environments by taking advantage of limitations of the human visual system. A model of visual attention is used to locate regions of interest in a scene and to…
Gradient information is widely useful and available in applications, and is therefore natural to include in the training of neural networks. Yet little is known theoretically about the impact of Sobolev training -- regression with both…
A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing…
The paper discusses the use of the Absolute activation function in classification neural networks. An examples are shown of using this activation function in simple and more complex problems. Using as a baseline LeNet-5 network for solving…
We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image…
How can a machine learn to recognize visual attributes emerging out of online community without a definitive supervised dataset? This paper proposes an automatic approach to discover and analyze visual attributes from a noisy collection of…
Graph neural networks (GNNs) demonstrate great performance in compound property and activity prediction due to their capability to efficiently learn complex molecular graph structures. However, two main limitations persist including…