Search Results for author: Soumik Sarkar

Found 73 papers, 15 papers with code

Latent Diffusion Models for Structural Component Design

no code implementations20 Sep 2023 Ethan Herron, Jaydeep Rade, Anushrut Jignasu, Baskar Ganapathysubramanian, Aditya Balu, Soumik Sarkar, Adarsh Krishnamurthy

Specifically, we employ a Latent Diffusion model to generate potential designs of a component that can satisfy a set of problem-specific loading conditions.

Image Generation

Active shooter detection and robust tracking utilizing supplemental synthetic data

no code implementations6 Sep 2023 Joshua R. Waite, Jiale Feng, Riley Tavassoli, Laura Harris, Sin Yong Tan, Subhadeep Chakraborty, Soumik Sarkar

The increasing concern surrounding gun violence in the United States has led to a focus on developing systems to improve public safety.

Transfer Learning

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos

1 code implementation16 Jun 2023 Md Zahid Hasan, Jiajing Chen, Jiyang Wang, Mohammed Shaiqur Rahman, Ameya Joshi, Senem Velipasalar, Chinmay Hegde, Anuj Sharma, Soumik Sarkar

Our results show that this framework offers state-of-the-art performance on zero-shot transfer and video-based CLIP for predicting the driver's state on two public datasets.

Activity Recognition

Out-of-distribution detection algorithms for robust insect classification

no code implementations2 May 2023 Mojdeh Saadati, Aditya Balu, Shivani Chiranjeevi, Talukder Zaki Jubery, Asheesh K Singh, Soumik Sarkar, Arti Singh, Baskar Ganapathysubramanian

One of the primary emphasis of researchers is to implement identification and classification models in the real agriculture fields, which is challenging because input images that are wildly out of the distribution (e. g., images like vehicles, animals, humans, or a blurred image of an insect or insect class that is not yet trained on) can produce an incorrect insect classification.

Classification Out-of-Distribution Detection +1

SpecXAI -- Spectral interpretability of Deep Learning Models

no code implementations20 Feb 2023 Stefan Druc, Peter Wooldridge, Adarsh Krishnamurthy, Soumik Sarkar, Aditya Balu

Deep learning is becoming increasingly adopted in business and industry due to its ability to transform large quantities of data into high-performing models.

Explainable Artificial Intelligence (XAI)

Neural PDE Solvers for Irregular Domains

no code implementations7 Nov 2022 Biswajit Khara, Ethan Herron, Zhanhong Jiang, Aditya Balu, Chih-Hsuan Yang, Kumar Saurabh, Anushrut Jignasu, Soumik Sarkar, Chinmay Hegde, Adarsh Krishnamurthy, Baskar Ganapathysubramanian

Neural network-based approaches for solving partial differential equations (PDEs) have recently received special attention.

Distributed Online Non-convex Optimization with Composite Regret

no code implementations21 Sep 2022 Zhanhong Jiang, Aditya Balu, Xian Yeow Lee, Young M. Lee, Chinmay Hegde, Soumik Sarkar

To address these two issues, we propose a novel composite regret with a new network regret-based metric to evaluate distributed online optimization algorithms.

Asynchronous Training Schemes in Distributed Learning with Time Delay

no code implementations28 Aug 2022 Haoxiang Wang, Zhanhong Jiang, Chao Liu, Soumik Sarkar, Dongxiang Jiang, Young M. Lee

In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance.

Concept Activation Vectors for Generating User-Defined 3D Shapes

no code implementations29 Apr 2022 Stefan Druc, Aditya Balu, Peter Wooldridge, Adarsh Krishnamurthy, Soumik Sarkar

We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD).

Stochastic Conservative Contextual Linear Bandits

no code implementations29 Mar 2022 Jiabin Lin, Xian Yeow Lee, Talukder Jubery, Shana Moothedath, Soumik Sarkar, Baskar Ganapathysubramanian

In this paper, we formulate a conservative stochastic contextual bandit formulation for real-time decision making when an adversary chooses a distribution on the set of possible contexts and the learner is subject to certain safety/performance constraints.

Decision Making Decision Making Under Uncertainty

MDPGT: Momentum-based Decentralized Policy Gradient Tracking

1 code implementation6 Dec 2021 Zhanhong Jiang, Xian Yeow Lee, Sin Yong Tan, Kai Liang Tan, Aditya Balu, Young M. Lee, Chinmay Hegde, Soumik Sarkar

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations.

Multi-agent Reinforcement Learning Policy Gradient Methods +3

Differentiable Spline Approximations

no code implementations NeurIPS 2021 Minsu Cho, Aditya Balu, Ameya Joshi, Anjana Deva Prasad, Biswajit Khara, Soumik Sarkar, Baskar Ganapathysubramanian, Adarsh Krishnamurthy, Chinmay Hegde

Overall, we show that leveraging this redesigned Jacobian in the form of a differentiable "layer" in predictive models leads to improved performance in diverse applications such as image segmentation, 3D point cloud reconstruction, and finite element analysis.

3D Point Cloud Reconstruction BIG-bench Machine Learning +3

NeuFENet: Neural Finite Element Solutions with Theoretical Bounds for Parametric PDEs

no code implementations4 Oct 2021 Biswajit Khara, Aditya Balu, Ameya Joshi, Soumik Sarkar, Chinmay Hegde, Adarsh Krishnamurthy, Baskar Ganapathysubramanian

We consider a mesh-based approach for training a neural network to produce field predictions of solutions to parametric partial differential equations (PDEs).

A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems

no code implementations24 Sep 2021 Xian Yeow Lee, Soumik Sarkar, YuBo Wang

We conduct further analysis on the impact of both observations and actions: on the observation end, we examine the robustness of graph-based policy on two typical data acquisition errors in power systems, namely sensor communication failure and measurement misalignment.

Reinforcement Learning (RL)

Distributed Deep Learning for Persistent Monitoring of agricultural Fields

no code implementations NeurIPS Workshop AI4Scien 2021 Yasaman Esfandiari, Koushik Nagasubramanian, Fateme Fotouhi, Patrick S. Schnable, Baskar Ganapathysubramanian, Soumik Sarkar

This continuous increase in the amount of data collected has created both the opportunity for, as well as the need to deploy distributed deep learning algorithms for a wide variety of decision support tasks in agriculture.

Anomaly Detection Image Retrieval +2

NURBS-Diff: A Differentiable Programming Module for NURBS

no code implementations29 Apr 2021 Anjana Deva Prasad, Aditya Balu, Harshil Shah, Soumik Sarkar, Chinmay Hegde, Adarsh Krishnamurthy

These derivatives are used to define an approximate Jacobian used for performing the "backward" evaluation to train the deep learning models.

BIG-bench Machine Learning Point cloud reconstruction

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data

1 code implementation2 Mar 2021 Yasaman Esfandiari, Sin Yong Tan, Zhanhong Jiang, Aditya Balu, Ethan Herron, Chinmay Hegde, Soumik Sarkar

Inspired by ideas from continual learning, we propose Cross-Gradient Aggregation (CGA), a novel decentralized learning algorithm where (i) each agent aggregates cross-gradient information, i. e., derivatives of its model with respect to its neighbors' datasets, and (ii) updates its model using a projected gradient based on quadratic programming (QP).

Continual Learning

A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment

1 code implementation19 Jan 2021 Homagni Saha, Fateme Fotouhif, Qisai Liu, Soumik Sarkar

In this paper we propose a new framework - MoViLan (Modular Vision and Language) for execution of visually grounded natural language instructions for day to day indoor household tasks.

Instruction Following Vision-Language Navigation

3D Convolutional Selective Autoencoder For Instability Detection in Combustion Systems

no code implementations6 Jan 2021 Tryambak Gangopadhyay, Vikram Ramanan, Adedotun Akintayo, Paige K Boor, Soumalya Sarkar, Satyanarayanan R Chakravarthy, Soumik Sarkar

3D-CSAE consists of filters to learn, in a hierarchical fashion, the complex visual and dynamic features related to combustion instability.

Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization

no code implementations9 Dec 2020 Jaydeep Rade, Aditya Balu, Ethan Herron, Jay Pathak, Rishikesh Ranade, Soumik Sarkar, Adarsh Krishnamurthy

We achieve this by training multiple networks, each learning a different step of the overall topology optimization methodology, making the framework more consistent with the topology optimization algorithm.

BIG-bench Machine Learning

Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents

1 code implementation13 Nov 2020 Xian Yeow Lee, Yasaman Esfandiari, Kai Liang Tan, Soumik Sarkar

As the complexity of CPS evolved, the focus has shifted from traditional control methods to deep reinforcement learning-based (DRL) methods for control of these systems.

reinforcement-learning Reinforcement Learning (RL) +1

Decentralized Deep Learning using Momentum-Accelerated Consensus

no code implementations21 Oct 2020 Aditya Balu, Zhanhong Jiang, Sin Yong Tan, Chinmay Hedge, Young M Lee, Soumik Sarkar

In this context, we propose and analyze a novel decentralized deep learning algorithm where the agents interact over a fixed communication topology (without a central server).

Few shot clustering for indoor occupancy detection with extremely low-quality images from battery free cameras

1 code implementation13 Aug 2020 Homagni Saha, Sin Yon Tan, Ali Saffari, Mohamad Katanbaf, Joshua R. Smith, Soumik Sarkar

We propose a combined few shot learning and clustering algorithm to address this challenge that has very low commissioning and maintenance cost.

Clustering Few-Shot Learning +1

Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretation

2 code implementations11 Aug 2020 Tryambak Gangopadhyay, Sin Yong Tan, Zhanhong Jiang, Rui Meng, Soumik Sarkar

Accurate interpretation of such prediction outcomes from a machine learning model that explicitly captures temporal correlations can significantly benefit the domain experts.

BIG-bench Machine Learning Time Series +1

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

no code implementations24 Jul 2020 Sergio Botelho, Ameya Joshi, Biswajit Khara, Soumik Sarkar, Chinmay Hegde, Santi Adavani, Baskar Ganapathysubramanian

Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements.

Distributed Computing

Robustifying Reinforcement Learning Agents via Action Space Adversarial Training

no code implementations14 Jul 2020 Kai Liang Tan, Yasaman Esfandiari, Xian Yeow Lee, Aakanksha, Soumik Sarkar

While robust control has a long history of development, robust ML is an emerging research area that has already demonstrated its relevance and urgency.

reinforcement-learning Reinforcement Learning (RL)

Usefulness of interpretability methods to explain deep learning based plant stress phenotyping

no code implementations11 Jul 2020 Koushik Nagasubramanian, Asheesh K. Singh, Arti Singh, Soumik Sarkar, Baskar Ganapathysubramanian

For some images, the output of the interpretability methods indicated that spurious feature correlations may have been used to correctly classify them.

Classification General Classification

Crop Yield Prediction Integrating Genotype and Weather Variables Using Deep Learning

no code implementations24 Jun 2020 Johnathon Shook, Tryambak Gangopadhyay, Linjiang Wu, Baskar Ganapathysubramanian, Soumik Sarkar, Asheesh K. Singh

Accurate prediction of crop yield supported by scientific and domain-relevant insights, can help improve agricultural breeding, provide monitoring across diverse climatic conditions and thereby protect against climatic challenges to crop production including erratic rainfall and temperature variations.

Crop Yield Prediction Explainable Models +1

How useful is Active Learning for Image-based Plant Phenotyping?

1 code implementation7 Jun 2020 Koushik Nagasubramanian, Talukder Z. Jubery, Fateme Fotouhi Ardakani, Seyed Vahid Mirnezami, Asheesh K. Singh, Arti Singh, Soumik Sarkar, Baskar Ganapathysubramanian

To overcome this challenge, active learning algorithms have been proposed that reduce the amount of labeling needed by deep learning models to achieve good predictive performance.

Active Learning General Classification +1

Deep Reinforcement Learning for Adaptive Traffic Signal Control

no code implementations14 Nov 2019 Kai Liang Tan, Subhadipto Poddar, Anuj Sharma, Soumik Sarkar

In this paper, we propose a DRL-based adaptive traffic signal control framework that explicitly considers realistic traffic scenarios, sensors, and physical constraints.

reinforcement-learning Reinforcement Learning (RL)

A perspective on multi-agent communication for information fusion

1 code implementation9 Nov 2019 Homagni Saha, Vijay Venkataraman, Alberto Speranzon, Soumik Sarkar

Collaborative decision making in multi-agent systems typically requires a predefined communication protocol among agents.

Decision Making

A Fast Saddle-Point Dynamical System Approach to Robust Deep Learning

1 code implementation18 Oct 2019 Yasaman Esfandiari, Aditya Balu, Keivan Ebrahimi, Umesh Vaidya, Nicola Elia, Soumik Sarkar

Under the assumptions that the cost function is convex and uncertainties enter concavely in the robust learning problem, we analytically show that our algorithm converges asymptotically to the robust optimal solution under a general adversarial budget constraints as induced by $\ell_p$ norm, for $1\leq p\leq \infty$.

On Higher-order Moments in Adam

no code implementations15 Oct 2019 Zhanhong Jiang, Aditya Balu, Sin Yong Tan, Young M. Lee, Chinmay Hegde, Soumik Sarkar

In this paper, we investigate the popular deep learning optimization routine, Adam, from the perspective of statistical moments.

Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents

1 code implementation5 Sep 2019 Xian Yeow Lee, Sambit Ghadai, Kai Liang Tan, Chinmay Hegde, Soumik Sarkar

In this work, we first frame the problem as an optimization problem of minimizing the cumulative reward of an RL agent with decoupled constraints as the budget of attack.

reinforcement-learning Reinforcement Learning (RL)

Learning to Cope with Adversarial Attacks

no code implementations28 Jun 2019 Xian Yeow Lee, Aaron Havens, Girish Chowdhary, Soumik Sarkar

Hence, it is imperative that RL agents deployed in real-life applications have the capability to detect and mitigate adversarial attacks in an online fashion.

Decision Making Meta-Learning

Encoding Invariances in Deep Generative Models

no code implementations4 Jun 2019 Viraj Shah, Ameya Joshi, Sambuddha Ghosal, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian, Chinmay Hegde

Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions.

Driver Behavior Analysis Using Lane Departure Detection Under Challenging Conditions

no code implementations31 May 2019 Luis Riera, Koray Ozcan, Jennifer Merickel, Mathew Rizzo, Soumik Sarkar, Anuj Sharma

Among the several deep learning architectures, convolutional neural networks (CNNs) outperformed other machine learning models, especially for region proposal and object detection tasks.

Lane Detection object-detection +3

Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers

1 code implementation ICCV 2019 Ameya Joshi, Amitangshu Mukherjee, Soumik Sarkar, Chinmay Hegde

We propose a novel approach to generate such `semantic' adversarial examples by optimizing a particular adversarial loss over the range-space of a parametric conditional generative model.

Flow Shape Design for Microfluidic Devices Using Deep Reinforcement Learning

no code implementations29 Nov 2018 Xian Yeow Lee, Aditya Balu, Daniel Stoecklein, Baskar Ganapathysubramanian, Soumik Sarkar

A particularly popular form of microfluidics -- called inertial microfluidic flow sculpting -- involves placing a sequence of pillars to controllably deform an initial flow field into a desired one.

reinforcement-learning Reinforcement Learning (RL)

3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys

no code implementations23 Nov 2018 Rahul Singh, Aayush Sharma, Onur Rauf Bingol, Aditya Balu, Ganesh Balasubramanian, Duane D. Johnson, Soumik Sarkar

In this paper, we explore a deep convolutional neural-network based approach to develop the atomistic potential for such complex alloys to investigate materials for insights into controlling properties.

Physics-aware Deep Generative Models for Creating Synthetic Microstructures

no code implementations21 Nov 2018 Rahul Singh, Viraj Shah, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian, Chinmay Hegde

The first model is a WGAN model that uses a finite number of training images to synthesize new microstructures that weakly satisfy the physical invariances respected by the original data.

Stochastic Optimization

Online Robust Policy Learning in the Presence of Unknown Adversaries

no code implementations NeurIPS 2018 Aaron J. Havens, Zhanhong Jiang, Soumik Sarkar

The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents.

OpenAI Gym reinforcement-learning +1

Root-cause Analysis for Time-series Anomalies via Spatiotemporal Graphical Modeling in Distributed Complex Systems

no code implementations31 May 2018 Chao Liu, Kin Gwn Lore, Zhanhong Jiang, Soumik Sarkar

Performance monitoring, anomaly detection, and root-cause analysis in complex cyber-physical systems (CPSs) are often highly intractable due to widely diverse operational modes, disparate data types, and complex fault propagation mechanisms.

Anomaly Detection Time Series +1

Multi-level 3D CNN for Learning Multi-scale Spatial Features

1 code implementation30 May 2018 Sambit Ghadai, Xian Lee, Aditya Balu, Soumik Sarkar, Adarsh Krishnamurthy

The multi-level voxel representation consists of a coarse voxel grid that contains volumetric information of the 3D object.

3D Object Recognition

On Consensus-Optimality Trade-offs in Collaborative Deep Learning

no code implementations30 May 2018 Zhanhong Jiang, Aditya Balu, Chinmay Hegde, Soumik Sarkar

In distributed machine learning, where agents collaboratively learn from diverse private data sets, there is a fundamental tension between consensus and optimality.


Interpretable Deep Learning applied to Plant Stress Phenotyping

no code implementations24 Oct 2017 Sambuddha Ghosal, David Blystone, Asheesh K. Singh, Baskar Ganapathysubramanian, Arti Singh, Soumik Sarkar

Availability of an explainable deep learning model that can be applied to practical real world scenarios and in turn, can consistently, rapidly and accurately identify specific and minute traits in applicable fields of biological sciences, is scarce.

General Classification Transfer Learning

Collaborative Deep Learning in Fixed Topology Networks

no code implementations NeurIPS 2017 Zhanhong Jiang, Aditya Balu, Chinmay Hegde, Soumik Sarkar

There is significant recent interest to parallelize deep learning algorithms in order to handle the enormous growth in data and model sizes.

Energy Prediction using Spatiotemporal Pattern Networks

no code implementations3 Feb 2017 Zhanhong Jiang, Chao Liu, Adedotun Akintayo, Gregor Henze, Soumik Sarkar

This paper presents a novel data-driven technique based on the spatiotemporal pattern network (STPN) for energy/power prediction for complex dynamical systems.

A Bayesian Network approach to County-Level Corn Yield Prediction using historical data and expert knowledge

no code implementations17 Aug 2016 Vikas Chawla, Hsiang Sing Naik, Adedotun Akintayo, Dermot Hayes, Patrick Schnable, Baskar Ganapathysubramanian, Soumik Sarkar

In this paper, we propose a data-driven approach that is "gray box" i. e. that seamlessly utilizes expert knowledge in constructing a statistical network model for corn yield forecasting.


Data-driven root-cause analysis for distributed system anomalies

no code implementations20 May 2016 Chao Liu, Kin Gwn Lore, Soumik Sarkar

Modern distributed cyber-physical systems encounter a large variety of anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems.

Multi-class Classification

Deep Action Sequence Learning for Causal Shape Transformation

no code implementations17 May 2016 Kin Gwn Lore, Daniel Stoecklein, Michael Davies, Baskar Ganapathysubramanian, Soumik Sarkar

Deep learning became the method of choice in recent year for solving a wide variety of predictive analytics tasks.

Decision Making

Early Detection of Combustion Instabilities using Deep Convolutional Selective Autoencoders on Hi-speed Flame Video

no code implementations25 Mar 2016 Adedotun Akintayo, Kin Gwn Lore, Soumalya Sarkar, Soumik Sarkar

With such a training scheme, the selective autoencoder is shown to be able to detect subtle instability features as a combustion process makes transition from stable to unstable region.


An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS

no code implementations24 Dec 2015 Chao Liu, Sambuddha Ghosal, Zhanhong Jiang, Soumik Sarkar

Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems.

Anomaly Detection

LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement

4 code implementations12 Nov 2015 Kin Gwn Lore, Adedotun Akintayo, Soumik Sarkar

In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the success of an operation.

Denoising Low-Light Image Enhancement

Occlusion Edge Detection in RGB-D Frames using Deep Convolutional Networks

no code implementations22 Dec 2014 Soumik Sarkar, Vivek Venugopalan, Kishore Reddy, Michael Giering, Julian Ryde, Navdeep Jaitly

Occlusion edges in images which correspond to range discontinuity in the scene from the point of view of the observer are an important prerequisite for many vision and mobile robot tasks.

Edge Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.