Rohan Ghosh

Rohan Ghosh

Auto-generated profile, based on publicly available information

Rohan Ghosh

Department of Electrical and Computer Engineering, National University of Singapore

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2016
Verified
Conference Paper
Closed access
FSFrancesca Sorgini
Francesca Sorgini
RGRohan Ghosh
Rohan Ghosh
JHJustus F. Huebotter
Justus F. Huebotter
RCRenato Calio
Renato Calio
Carmen GalassiCarmen Galassi
Carmen Galassi
SKSunil L. Kukreja
Sunil L. Kukreja
During the last decade significant advances have been made in vibrotactile actuator design that are leading to the development of novel haptic technologies. Similarly, important innovations have been made in the area of virtual reality for scene rendering and user tracking. However, the integration of these technologies has not been well explored. In this paper, we outline a broad design philosophy and integration plan of these tools. In addition, we give an overview of applications for such a cohesive set of technologies. Preliminary results are provided to demonstrate their critical importance and future widespread use.

1 October 2016
Verified
Conference Paper
Closed access
STSiyi Tang
Siyi Tang
RGRohan Ghosh
Rohan Ghosh
NTNitish Thakor
Nitish Thakor
SKSunil L. Kukreja
Sunil L. Kukreja
In this demonstration we show improved grasping capabilities of household objects by an upper limb prosthesis using the unique features of a dynamic vision sensor (DVS). With the low-power consumption and non-redundant data output of a DVS, our system is able to perform real-time object classification and optimal grasp orientation. This enables an amputee to simply approach an object to be grasped by the prosthetic, while our novel algorithm assists with task completion. Our approach is motivated with the goal to reduce cognitive load required by amputees to control prosthetic hands.

31 January 2025 in TechRxiv
Verified
Preprint
Open access
SWShelvia Wongso
Shelvia Wongso
RGRohan Ghosh
Rohan Ghosh
MMMehul Motani
Mehul Motani
The Information Bottleneck theory offers a framework for understanding the learning dynamics of deep neural networks (DNNs) by analyzing the mutual information (MI) between inputs X and the network's feature representations T , I(X; T), and between T and outputs Y , I(T ; Y), on a plane. Despite its theoretical appeal, some limitations exist: for deterministic networks, the true I(X; T) is infinite, and estimating MI in high-dimensional spaces is notoriously difficult, often resulting in inconsistent empirical findings. In this work, we introduce the Sliced Information Plane (SIP), using Sliced Mutual Information (SMI) as an alternative to MI. The reason for utilizing SMI is that it is scalable to high dimensions and remains finite even with deterministic mappings. In our study, we visualize the SIP which captures the relationship between SI(X; T) (SMI between X and T) and SI(T ; Y) (SMI between T and Y). We show that the trends are consistent across different estimators and we utilize SIP to analyze the learning dynamics of DNNs under various settings. An interesting observation is during training, SI(X; T) initially decreases and then increases for deeper layers, suggesting that the network first discards what it deems irrelevant information from the input, only to later relearn some of this information, which it considers useful for predicting the label (increase in SI(T ; Y)).