Search Results for author:
Found 77 papers, 16 papers with code
DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models
This DIMAT paradigm presents a new opportunity for the future decentralized learning, enhancing its adaptability to real-world with sparse and light-weight communication and computation.
GENESIS-RL: GEnerating Natural Edge-cases with Systematic Integration of Safety considerations and Reinforcement Learning
In the rapidly evolving field of autonomous systems, the safety and reliability of the system components are fundamental requirements.
Multi-Sensor and Multi-temporal High-Throughput Phenotyping for Monitoring and Early Detection of Water-Limiting Stress in Soybean
We investigated a set of diverse soybean accessions using multiple sensors in a time series high-throughput phenotyping manner to: (1) develop a pipeline for rapid classification of soybean drought stress symptoms, and (2) investigate methods for early detection of drought stress.
Evaluating NeRFs for 3D Plant Geometry Reconstruction in Field Conditions
We evaluate different Neural Radiance Fields (NeRFs) techniques for reconstructing (3D) plants in varied environments, from indoor settings to outdoor fields.
Latent Diffusion Models for Structural Component Design
Specifically, we employ a Latent Diffusion model to generate potential designs of a component that can satisfy a set of problem-specific loading conditions.
Active shooter detection and robust tracking utilizing supplemental synthetic data
The increasing concern surrounding gun violence in the United States has led to a focus on developing systems to improve public safety.
Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos
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.
Deep learning powered real-time identification of insects using citizen science data
InsectNet can guide citizen science data collection, especially for invasive species where early detection is crucial.
Out-of-distribution detection algorithms for robust insect classification
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.
SpecXAI -- Spectral interpretability of Deep Learning Models
Deep learning is becoming increasingly adopted in business and industry due to its ability to transform large quantities of data into high-performing models.
3D Reconstruction of Protein Complex Structures Using Synthesized Multi-View AFM Images
These multi-view images can help train the neural network to predict the 3D structure of protein complexes.
Neural PDE Solvers for Irregular Domains
Neural network-based approaches for solving partial differential equations (PDEs) have recently received special attention.
Distributed Online Non-convex Optimization with Composite Regret
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
In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance.
A Deep Learning Approach to Detect Lean Blowout in Combustion Systems
However, approaching towards lean combustion can make engines more susceptible to lean blowout.
Concept Activation Vectors for Generating User-Defined 3D Shapes
We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD).
Stochastic Conservative Contextual Linear Bandits
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.
MDPGT: Momentum-based Decentralized Policy Gradient Tracking
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
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.
NeuFENet: Neural Finite Element Solutions with Theoretical Bounds for Parametric PDEs
We consider a mesh-based approach for training a neural network to produce field predictions of solutions to parametric partial differential equations (PDEs).
Cross-Modal Virtual Sensing for Combustion Instability Monitoring
However, flame imaging is not a common sensing modality in engine combustors today.
A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems
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.
Distributed Deep Learning for Persistent Monitoring of agricultural Fields
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.
NURBS-Diff: A Differentiable Programming Module for NURBS
These derivatives are used to define an approximate Jacobian used for performing the "backward" evaluation to train the deep learning models.
Distributed Multigrid Neural Solvers on Megavoxel Domains
We specifically consider neural solvers for the generalized 3D Poisson equation over megavoxel domains.
Granger Causality Based Hierarchical Time Series Clustering for State Estimation
Clustering is an unsupervised learning technique that is useful when working with a large volume of unlabeled data.
Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
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).
A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment
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.
3D Convolutional Selective Autoencoder For Instability Detection in Combustion Systems
3D-CSAE consists of filters to learn, in a hierarchical fashion, the complex visual and dynamic features related to combustion instability.
Differentiable Programming for Piecewise Polynomial Functions
The paradigm of differentiable programming has considerably enhanced the scope of machine learning via the judicious use of gradient-based optimization.
Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization
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.
Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents
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.
Deep Multi-view Image Fusion for Soybean Yield Estimation in Breeding Applications Deep Multi-view Image Fusion for Soybean Yield Estimation in Breeding Applications
The objective of this study is to develop a machine learning (ML) approach adept at soybean [\textit{Glycine max} L.
Decentralized Deep Learning using Momentum-Accelerated Consensus
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
We propose a combined few shot learning and clustering algorithm to address this challenge that has very low commissioning and maintenance cost.
Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretation
Accurate interpretation of such prediction outcomes from a machine learning model that explicitly captures temporal correlations can significantly benefit the domain experts.
Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models
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.
Robustifying Reinforcement Learning Agents via Action Space Adversarial Training
While robust control has a long history of development, robust ML is an emerging research area that has already demonstrated its relevance and urgency.
Usefulness of interpretability methods to explain deep learning based plant stress phenotyping
For some images, the output of the interpretability methods indicated that spurious feature correlations may have been used to correctly classify them.
Crop Yield Prediction Integrating Genotype and Weather Variables Using Deep Learning
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.
How useful is Active Learning for Image-based Plant Phenotyping?
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.
Deep Reinforcement Learning for Adaptive Traffic Signal Control
In this paper, we propose a DRL-based adaptive traffic signal control framework that explicitly considers realistic traffic scenarios, sensors, and physical constraints.
A perspective on multi-agent communication for information fusion
Collaborative decision making in multi-agent systems typically requires a predefined communication protocol among agents.
A Fast Saddle-Point Dynamical System Approach to Robust Deep Learning
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
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
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.
Learning to Cope with Adversarial Attacks
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.
Encoding Invariances in Deep Generative Models
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
Among the several deep learning architectures, convolutional neural networks (CNNs) outperformed other machine learning models, especially for region proposal and object detection tasks.
Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
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
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.
3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys
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
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.
Interpretable deep learning for guided structure-property explorations in photovoltaics
The performance of an organic photovoltaic device is intricately connected to its active layer morphology.
Online Robust Policy Learning in the Presence of Unknown Adversaries
The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents.
Root-cause Analysis for Time-series Anomalies via Spatiotemporal Graphical Modeling in Distributed Complex Systems
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.
Predicting County Level Corn Yields Using Deep Long Short Term Memory Models
Corn yield prediction is beneficial as it provides valuable information about production and prices prior the harvest.
Multi-level 3D CNN for Learning Multi-scale Spatial Features
The multi-level voxel representation consists of a coarse voxel grid that contains volumetric information of the 3D object.
On Consensus-Optimality Trade-offs in Collaborative Deep Learning
In distributed machine learning, where agents collaboratively learn from diverse private data sets, there is a fundamental tension between consensus and optimality.
Explaining hyperspectral imaging based plant disease identification: 3D CNN and saliency maps
We identify the most sensitive wavelength as 733 nm using the saliency map visualization.
A Forward-Backward Approach for Visualizing Information Flow in Deep Networks
We introduce a new, systematic framework for visualizing information flow in deep networks.
Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes
3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object.
Interpretable Deep Learning applied to Plant Stress Phenotyping
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.
Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean
The focus of this work is to determine the minimal number of most effective hyperspectral bands that can distinguish between healthy and diseased specimens early in the growing season.
Collaborative Deep Learning in Fixed Topology Networks
There is significant recent interest to parallelize deep learning algorithms in order to handle the enormous growth in data and model sizes.
A Machine-Learning Framework for Design for Manufacturability
this is a duplicate submission(original is arXiv:1612. 02141).
Hierarchical Symbolic Dynamic Filtering of Streaming Non-stationary Time Series Data
The algorithm minimizes model complexity and captures data likelihood.
Energy Prediction using Spatiotemporal Pattern Networks
This paper presents a novel data-driven technique based on the spatiotemporal pattern network (STPN) for energy/power prediction for complex dynamical systems.
Learning Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes
3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object.
A Bayesian Network approach to County-Level Corn Yield Prediction using historical data and expert knowledge
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
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.
Deep Action Sequence Learning for Causal Shape Transformation
Deep learning became the method of choice in recent year for solving a wide variety of predictive analytics tasks.
Early Detection of Combustion Instabilities using Deep Convolutional Selective Autoencoders on Hi-speed Flame Video
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 end-to-end convolutional selective autoencoder approach to Soybean Cyst Nematode eggs detection
This paper proposes a novel selective autoencoder approach within the framework of deep convolutional networks.
An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS
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.
LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement
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.
Occlusion Edge Detection in RGB-D Frames using Deep Convolutional Networks
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.
