Search Results - "Vasudevan, Shrihari"
-
1
Mutual Information Based Learning Rate Decay for Stochastic Gradient Descent Training of Deep Neural Networks
Published in Entropy (Basel, Switzerland) (17-05-2020)“…This paper demonstrates a novel approach to training deep neural networks using a Mutual Information (MI)-driven, decaying Learning Rate (LR), Stochastic…”
Get full text
Journal Article -
2
Bayesian space conceptualization and place classification for semantic maps in mobile robotics
Published in Robotics and autonomous systems (30-06-2008)“…The future of robots, as our companions is dependent on their ability to understand, interpret and represent the environment in a human compatible manner…”
Get full text
Journal Article -
3
Gaussian process modeling of large-scale terrain
Published in Journal of field robotics (01-10-2009)“…Building a model of large‐scale terrain that can adequately handle uncertainty and incompleteness in a statistically sound way is a challenging problem. This…”
Get full text
Journal Article -
4
Efficacy of Data Fusion Using Convolved Multi-Output Gaussian Processes
Published in Journal of Data Science (08-04-2021)Get full text
Journal Article -
5
AN EMPIRICAL STUDY OF STARTING SALARIES AND EMPLOYMENT TRENDS OF ENGINEERING STUDENTS IN INDIA
Published in Journal of Data Science (07-03-2021)“…This paper presents an empirical study of a recently compiled workforce analytics data-set modeling employment outcomes of Engineering students. The…”
Get full text
Journal Article -
6
Estimating Fungibility Between Skills by Combining Skill Similarities Obtained from Multiple Data Sources
Published in Data science and engineering (01-09-2018)“…This paper proposes an approach to estimating fungibility between skills given multiple information sources of those skills. An estimate of skill adjacency or…”
Get full text
Journal Article -
7
Data fusion with Gaussian processes
Published in Robotics and autonomous systems (01-12-2012)“…This paper addresses the problem of fusing multiple sets of heterogeneous sensor data using Gaussian processes (GPs). Experiments on large scale terrain…”
Get full text
Journal Article -
8
Cognitive maps for mobile robots—an object based approach
Published in Robotics and autonomous systems (31-05-2007)“…Robots are rapidly evolving from factory work-horses to robot-companions. The future of robots, as our companions, is highly dependent on their abilities to…”
Get full text
Journal Article -
9
Estimating Task Completion Times for Network Rollouts using Statistical Models within Partitioning-based Regression Methods
Published in 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS) (03-01-2023)“…This paper proposes a data and Machine Learning-based forecasting solution for the Telecommunications network-rollout planning problem. Milestone…”
Get full text
Conference Proceeding -
10
Bayesian Regression for Interpretable Network Dimensioning
Published in 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS) (03-01-2023)“…This paper proposes a solution to learn interpretable regression models for the Telecommunications industry's network dimensioning problem. Domain knowledge in…”
Get full text
Conference Proceeding -
11
Non-stationary dependent Gaussian processes for data fusion in large-scale terrain modeling
Published in 2011 IEEE International Conference on Robotics and Automation (01-05-2011)“…Obtaining a comprehensive model of large and complex terrain typically entails the use of both multiple sensory modalities and multiple data sets. This paper…”
Get full text
Conference Proceeding -
12
Dynamic learning rate using Mutual Information
Published 18-05-2018“…This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied…”
Get full text
Journal Article -
13
A Mine on Its Own
Published in IEEE robotics & automation magazine (01-06-2010)“…This article presents a study of Gaussian process (GP) models applied to the problems of modeling and data fusion in the context of large-scale terrain…”
Get full text
Journal Article -
14
Estimating Task Completion Times for Network Rollouts using Statistical Models within Partitioning-based Regression Methods
Published 19-11-2022“…This paper proposes a data and Machine Learning-based forecasting solution for the Telecommunications network-rollout planning problem. Milestone…”
Get full text
Journal Article -
15
Sequential Binary Classification for Intrusion Detection in Software Defined Networks
Published 10-06-2024“…Software-Defined Networks (SDN) are the standard architecture for network deployment. Intrusion Detection Systems (IDS) are a pivotal part of this technology…”
Get full text
Journal Article -
16
-
17
Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot
Published in Journal of intelligent & robotic systems (01-11-2012)“…This paper addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key…”
Get full text
Journal Article Publication -
18
Layer Dynamics of Linearised Neural Nets
Published 24-04-2019“…Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets. More research…”
Get full text
Journal Article -
19
Large-scale terrain modeling from multiple sensors with dependent Gaussian processes
Published in 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (01-10-2010)“…Terrain modeling remains a challenging yet key component for the deployment of ground robots to the field. The difficulty arrives from the variability of…”
Get full text
Conference Proceeding -
20
Data-Efficient Automatic Model Selection in Unsupervised Anomaly Detection
Published in 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA) (01-12-2022)“…Anomaly Detection is a widely used technique in machine learning that identifies context-specific outliers. Most real-world anomaly detection applications are…”
Get full text
Conference Proceeding