Search
Now showing items 11-20 of 48
Time-correlated sparsification for communication-efficient federated learning
(IEEE, 2021)
Federated learning (FL) enables multiple clients to collaboratively train a shared model, with the help of a parameter server (PS), without disclosing their local datasets. However, due to the increasing size of the trained ...
Dynamic filtering and prioritization of static code analysis alerts
(IEEE, 2021)
We propose an approach for filtering and prioritizing static code analysis alerts while these alerts are being reviewed by the developer. We construct a Prolog knowledge base that captures the data flow information in the ...
Data model extension impact analysis
(IEEE, 2021)
Relational database schemas are subject to change. For instance, columns of a table can be modified, deleted or extended. These changes have an impact on the source code that utilizes the corresponding table. They also ...
Road to salvation: Streaming clients and content delivery networks working together
(IEEE, 2021-11-01)
Streaming media has truly become one of the most popular applications on the Internet. Viewers are spoiled for choice, and content providers compete to provide the best viewer experience. Traditionally, it has been challenging ...
Weight update skipping: Reducing training time for artificial neural networks
(IEEE, 2021-12)
Artificial Neural Networks (ANNs) are known as state-of-the-art techniques in Machine Learning (ML) and have achieved outstanding results in data-intensive applications, such as recognition, classification, and segmentation. ...
Misclassification risk and uncertainty quantification in deep classifiers
(IEEE, 2021)
In this paper, we propose risk-calibrated evidential deep classifiers to reduce the costs associated with classification errors. We use two main approaches. The first is to develop methods to quantify the uncertainty of a ...
Learning system dynamics via deep recurrent and conditional neural systems
(IEEE, 2021)
Although there are various mathematical methods for modeling system dynamics, more general solutions can be achieved using deep learning based on data. Alternative deep learning methods are presented in parallel with the ...
Trust me! I am a robot: an affective computational account of scaffolding in robot-robot interaction
(IEEE, 2021-08-08)
Forming trust in a biological or artificial interaction partner that provides reliable strategies and employing the learned strategies to scaffold another agent are critical problems that are often addressed separately in ...
Effect regulated projection of robot’s action space for production and prediction of manipulation primitives through learning progress and predictability based exploration
(IEEE, 2021-06)
In this study, we propose an effective action parameter exploration mechanism that enables efficient discovery of robot actions through interacting with objects in a simulated table-top environment. For this, the robot ...
Data-driven bandwidth prediction models and automated model selection for low latency
(IEEE, 2021)
Today's HTTP adaptive streaming solutions use a variety of algorithms to measure the available network bandwidth and predict its future values. Bandwidth prediction, which is already a difficult task, must be more accurate ...
Share this page