49 citations · 73 across the 14 of their papers we have counts for
15 papers
DietCNN: Multiplication-free Inference for Quantized CNNs
Swarnava Dey, Pallab Dasgupta, Partha P Chakrabarti
The rising demand for networked embedded systems with machine intelligence has been a catalyst for sustained attempts by the research community to implement Convolutional Neural Ne…
Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity
Kaushik Dey, Satheesh K. Perepu, Pallab Dasgupta +1
The dynamic and evolutionary nature of service requirements in wireless networks has motivated the telecom industry to consider intelligent self-adapting Reinforcement Learning (RL…
Penalizing Proposals using Classifiers for Semi-Supervised Object Detection
Somnath Hazra, Pallab Dasgupta
Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a smal…
Methodology for Biasing Random Simulation for Rapid Coverage of Corner Cases in AMS Designs
Sayandeep Sanyal, Ayan Chakraborty, Pallab Dasgupta +1
Exploring the limits of an Analog and Mixed Signal (AMS) circuit by driving appropriate inputs has been a serious challenge to the industry. Doing an exhaustive search of the entir…
Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving
Briti Gangopadhyay, Harshit Soora, Pallab Dasgupta
Recent advances in Reinforcement Learning (RL) combined with Deep Learning (DL) have demonstrated impressive performance in complex tasks, including autonomous driving. The use of…
Quantitative Corner Case Feature Analysis of Hybrid Automata with ForFET
Antonio Anastasio Bruto da Costa, Pallab Dasgupta, Nikolaos Kekatos
The analysis and verification of hybrid automata (HA) models against rich formal properties can be a challenging task. Existing methods and tools can mainly reason whether a given…
Recurrence in Dense-time AMS Assertions
Sayandeep Sanyal, Antonio Anastasio Bruto da Costa, Pallab Dasgupta
The notion of recurrence over continuous or dense time, as required for expressing Analog and Mixed-Signal (AMS) behaviours, is fundamentally different from what is offered by the…
Early-Stage Resource Estimation from Functional Reliability Specification in Embedded Cyber-Physical Systems
Ginju V. George, Aritra Hazra, Pallab Dasgupta +1
Reliability and fault tolerance are critical attributes of embedded cyber-physical systems that require a high safety-integrity level. For such systems, the use of formal functiona…
Semi-Lexical Languages -- A Formal Basis for Unifying Machine Learning and Symbolic Reasoning in Computer Vision
Briti Gangopadhyay, Somnath Hazra, Pallab Dasgupta
Human vision is able to compensate imperfections in sensory inputs from the real world by reasoning based on prior knowledge about the world. Machine learning has had a significant…
Learning Temporal Causal Sequence Relationships from Real-Time Time-Series
Antonio Anastasio Bruto da Costa, Pallab Dasgupta
We aim to mine temporal causal sequences that explain observed events (consequents) in time-series traces. Causal explanations of key events in a time-series has applications in de…
Formal Feature Interpretation of Hybrid Systems
Antonio Anastasio Bruto da Costa, Goran Frehse, Pallab Dasgupta
In current practice a formal analysis of hybrid system models is assertion-based. The work presented here is based on features that look beyond functional correctness toward a quan…
Multi-mode Sampling Period Selection for Embedded Real Time Control
Rajorshee Raha, Soumyajit Dey, Partha Pratim Chakrabarti +1
Recent studies have shown that adaptively regulating the sampling rate results in significant reduction in computational resources in embedded software based control. Selecting a u…
Algorithms for Generating Ordered Solutions for Explicit AND/OR Structures
Priyankar Ghosh, Amit Sharma, P. P. Chakrabarti +1
We present algorithms for generating alternative solutions for explicit acyclic AND/OR structures in non-decreasing order of cost. The proposed algorithms use a best first search t…
A Multi-objective Perspective for Operator Scheduling using Fine-grained DVS Architecture
Rajdeep Mukherjee, Priyankar Ghosh, Pallab Dasgupta +1
The stringent power budget of fine grained power managed digital integrated circuits have driven chip designers to optimize power at the cost of area and delay, which were the trad…
Detecting Ontological Conflicts in Protocols between Semantic Web Services
Priyankar Ghosh, Pallab Dasgupta
The task of verifying the compatibility between interacting web services has traditionally been limited to checking the compatibility of the interaction protocol in terms of messag…