Ankita Shukla
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ankita Shukla has a total of 75 co-authors. Here are the top co-authors by number of shared publications:
- Pavan Turaga
Arizona State University
6 shared publications - Derek A. Mariscal
Lawrence Livermore National Laboratory 2 , Livermore, California 94550
2 shared publications Pavan Turaga
Arizona State University, Tempe, USA
2 shared publications- Peer-Timo Bremer
Computing Directorate, Lawrence Livermore National Laboratory, Livermore, CA
2 shared publications Rajhans Singh
Geometric Media Lab, Arizona State University, Tempe, AZ, United States
2 shared publications- Rushil Anirudh
Lawrence Livermore National Laboratory
2 shared publications
Latest Publications
- Open Access
Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to improve token robustness through a corruption-reconstruction framework. Unlike traditional mask-based reconstruction tasks that hide data segments for later prediction, Point-RTD corrupts point cloud tokens and leverages a discriminator-generator architecture for denoising. This shift enables more effective learning of structural priors and significantly enhances model performance and efficiency. On the ShapeNet dataset, Point-RTD reduces reconstruction error by over 93% compared to PointMAE, and achieves more than 14x lower Chamfer Distance on the test set. Our method also converges faster and yields higher classification accuracy on ShapeNet, ModelNet10, and ModelNet40 benchmarks, clearly outperforming the baseline Point-MAE framework in every case.
Open AccessPoint-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to improve token robustness through a corruption-reconstruction framework. Unlike traditional mask-based reconstruction tasks that hide data segments for later prediction, Point-RTD corrupts point cloud tokens and leverages a discriminator-generator architecture for denoising. This shift enables more effective learning of structural priors and significantly enhances model performance and efficiency. On the ShapeNet dataset, Point-RTD reduces reconstruction error by over 93% compared to PointMAE, and achieves more than 14x lower Chamfer Distance on the test set. Our method also converges faster and yields higher classification accuracy on ShapeNet, ModelNet10, and ModelNet40 benchmarks, clearly outperforming the baseline Point-MAE framework in every case.
- Open Access
- 8 January 2025
- Published by Springer Nature in Communications Physics
- Vol. 8 (1) , 1-11
On the design and evaluation of generative models in high energy density physics
- 8 January 2025
- Published by Springer Nature in Communications Physics
- Vol. 8 (1) , 1-11
Open AccessOn the design and evaluation of generative models in high energy density physics
- 20 December 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (5) , 2967-2995
Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models
- 20 December 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (5) , 2967-2995
Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models
- Open Access
- 1 July 2024
- Published by AIP Publishing in Physics of Plasmas
- Vol. 31 (7)
Toward machine-learning-assisted PW-class high-repetition-rate experiments with solid targets
We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such a framework for future autonomous exploration platforms in high-repetition-rate experiments.
- 1 July 2024
- Published by AIP Publishing in Physics of Plasmas
- Vol. 31 (7)
Open AccessToward machine-learning-assisted PW-class high-repetition-rate experiments with solid targets
We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such a framework for future autonomous exploration platforms in high-repetition-rate experiments.
- Open Access
- 10 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
On the impact of pre-training datasets for matching dendritic identifiers using residual nets
Dendrites are easy to synthesize branching structures that exhibit randomness; yet they are unique, non-repeatable, and identifiable with the right algorithmic innovations. This has created a novel application area where manufactured dendritic structures are being used as product identifiers - essentially "fingerprints for things". Unlike barcodes, which are linear structures, dendrites exhibit spatial randomness. This, coupled with a unique optical signal generated by light scattering from material inhomogeneities, ensures that each dendrite is unique and unclonable. While there have not yet been any established methods on reading dendritic patterns for verification using image data, identifying dendrites using computer vision techniques could have high potential. Due to limited data and low variance, dendrite identification can be considered to be a fine-grained classification task. In this paper, we examine how the selection of pre-trained models influences dendrite classification. The dendrites we work with share similarity to human fingerprints, thus we begin with a model trained for matching fingerprint data to extract features relevant to dendrites. Additionally, we explore broader pre-training approaches, using ImageNet-1K for our second model and ImageNet-21K for our third model. Surprisingly, our results indicate that even with the visual similarity with human fingerprints, more general pre-training with common image datasets achieves better performance on dendrite classification.
- 10 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessOn the impact of pre-training datasets for matching dendritic identifiers using residual nets
Dendrites are easy to synthesize branching structures that exhibit randomness; yet they are unique, non-repeatable, and identifiable with the right algorithmic innovations. This has created a novel application area where manufactured dendritic structures are being used as product identifiers - essentially "fingerprints for things". Unlike barcodes, which are linear structures, dendrites exhibit spatial randomness. This, coupled with a unique optical signal generated by light scattering from material inhomogeneities, ensures that each dendrite is unique and unclonable. While there have not yet been any established methods on reading dendritic patterns for verification using image data, identifying dendrites using computer vision techniques could have high potential. Due to limited data and low variance, dendrite identification can be considered to be a fine-grained classification task. In this paper, we examine how the selection of pre-trained models influences dendrite classification. The dendrites we work with share similarity to human fingerprints, thus we begin with a model trained for matching fingerprint data to extract features relevant to dendrites. Additionally, we explore broader pre-training approaches, using ImageNet-1K for our second model and ImageNet-21K for our third model. Surprisingly, our results indicate that even with the visual similarity with human fingerprints, more general pre-training with common image datasets achieves better performance on dendrite classification.
- Open Access
- 22 May 2024
- Published by Frontiers Media SA in Frontiers in Computer Science
- Vol. 6, 1274779
Orthogonality and graph divergence losses promote disentanglement in generative models
Over the last decade, deep generative models have evolved to generate realistic and sharp images. The success of these models is often attributed to an extremely large number of trainable parameters and an abundance of training data, with limited or no understanding of the underlying data manifold. In this article, we explore the possibility of learning a deep generative model that is structured to better capture the underlying manifold's geometry, to effectively improve image generation while providing implicit controlled generation by design. Our approach structures the latent space into multiple disjoint representations capturing different attribute manifolds. The global representations are guided by a disentangling loss for effective attribute representation learning and a differential manifold divergence loss to learn an effective implicit generative model. Experimental results on a 3D shapes dataset demonstrate the model's ability to disentangle attributes without direct supervision and its controllable generative capabilities. These findings underscore the potential of structuring deep generative models to enhance image generation and attribute control without direct supervision with ground truth attributes signaling progress toward more sophisticated deep generative models.
- 22 May 2024
- Published by Frontiers Media SA in Frontiers in Computer Science
- Vol. 6, 1274779
Open AccessOrthogonality and graph divergence losses promote disentanglement in generative models
Over the last decade, deep generative models have evolved to generate realistic and sharp images. The success of these models is often attributed to an extremely large number of trainable parameters and an abundance of training data, with limited or no understanding of the underlying data manifold. In this article, we explore the possibility of learning a deep generative model that is structured to better capture the underlying manifold's geometry, to effectively improve image generation while providing implicit controlled generation by design. Our approach structures the latent space into multiple disjoint representations capturing different attribute manifolds. The global representations are guided by a disentangling loss for effective attribute representation learning and a differential manifold divergence loss to learn an effective implicit generative model. Experimental results on a 3D shapes dataset demonstrate the model's ability to disentangle attributes without direct supervision and its controllable generative capabilities. These findings underscore the potential of structuring deep generative models to enhance image generation and attribute control without direct supervision with ground truth attributes signaling progress toward more sophisticated deep generative models.
- 3 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
Constrained Adaptive Distillation Based on Topological Persistence for Wearable Sensor Data
Wearable sensor data analysis with persistence features generated by topological data analysis (TDA) has achieved great success in various applications, and however, it suffers from large computational and time resources for extracting topological features. In this article, our approach utilizes knowledge distillation (KD) that involves the use of multiple teacher networks trained with the raw time series and persistence images (PIs) generated by TDA. However, direct transfer of knowledge from the teacher models utilizing different characteristics as inputs to the student model results in a knowledge gap and limited performance. To address this problem, we introduce a robust framework that integrates multimodal features from two different teachers and enables a student to learn desirable knowledge effectively. To account for statistical differences in multimodalities, an entropy-based constrained adaptive weighting mechanism is leveraged to automatically balance the effects of teachers and encourage the student model to adequately adopt the knowledge from two teachers. To assimilate dissimilar structural information generated by different style models for distillation, batch and channel similarities within a mini-batch are used. We demonstrate the effectiveness of the proposed method on wearable sensor data.
- 3 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
Constrained Adaptive Distillation Based on Topological Persistence for Wearable Sensor Data
Wearable sensor data analysis with persistence features generated by topological data analysis (TDA) has achieved great success in various applications, and however, it suffers from large computational and time resources for extracting topological features. In this article, our approach utilizes knowledge distillation (KD) that involves the use of multiple teacher networks trained with the raw time series and persistence images (PIs) generated by TDA. However, direct transfer of knowledge from the teacher models utilizing different characteristics as inputs to the student model results in a knowledge gap and limited performance. To address this problem, we introduce a robust framework that integrates multimodal features from two different teachers and enables a student to learn desirable knowledge effectively. To account for statistical differences in multimodalities, an entropy-based constrained adaptive weighting mechanism is leveraged to automatically balance the effects of teachers and encourage the student model to adequately adopt the knowledge from two teachers. To assimilate dissimilar structural information generated by different style models for distillation, batch and channel similarities within a mini-batch are used. We demonstrate the effectiveness of the proposed method on wearable sensor data.
- Open Access
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4159-4168
Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant yet in a task-specific manner. The proposed model improves the final feature’s interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance compared to the baseline and standard ResNet models while substantially improving interpretability.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4159-4168
Open AccessImproving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments
Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant yet in a task-specific manner. The proposed model improves the final feature’s interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance compared to the baseline and standard ResNet models while substantially improving interpretability.
- Open Access
- 3 November 2022
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (21) , 14381
An Evaluation of Non-Communicable Diseases and Risk Factors Associated with COVID-19 Disease Severity in Dubai, United Arab Emirates: An Observational Retrospective Study
The aim of this study was to determine the prevalence of non-communicable diseases and their correlation with COVID-19 disease severity among patients infected in Dubai. Clinical and demographic data were extracted from hospital records of 34,687 COVID-19 patients who visited or were admitted into Dubai hospitals between 28 January 2020 and 30 September 2020. Prevalence of co-morbidities in COVID-19 patients were assessed. The main risk factors associated with COVID-19 disease severity were also identified using three regression models. All co-morbidities were significantly associated with COVID-19 severity in the bivariate analysis (p-value ≤ 0.05) except for vitamin-D deficiency and chronic lower respiratory diseases. Patients with ischemic heart diseases (AOR: 2.08; 95% CI: 1.37, 3.15), pulmonary and other heart diseases (AOR: 2.13; 95% CI: 1.36, 3.32) and chronic kidney diseases (AOR: 1.81; 95% CI: 1.01, 3.25) had higher odds of severe COVID-19 symptoms. Suffering from multiple co-morbidities increased the odds of developing severe COVID-19 symptoms substantially in comparison to having only one co-morbidity i.e., (AOR: 1.52; 95% CI 1.76–2.60) to (AOR: 2.33; 95% CI: 1.37, 3.97). Identifying these risk factors could assist in the early recognition of high-risk populations and ensure the most appropriate preventive measures and required medical management during the pandemic.
- 3 November 2022
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (21) , 14381
Open AccessAn Evaluation of Non-Communicable Diseases and Risk Factors Associated with COVID-19 Disease Severity in Dubai, United Arab Emirates: An Observational Retrospective Study
The aim of this study was to determine the prevalence of non-communicable diseases and their correlation with COVID-19 disease severity among patients infected in Dubai. Clinical and demographic data were extracted from hospital records of 34,687 COVID-19 patients who visited or were admitted into Dubai hospitals between 28 January 2020 and 30 September 2020. Prevalence of co-morbidities in COVID-19 patients were assessed. The main risk factors associated with COVID-19 disease severity were also identified using three regression models. All co-morbidities were significantly associated with COVID-19 severity in the bivariate analysis (p-value ≤ 0.05) except for vitamin-D deficiency and chronic lower respiratory diseases. Patients with ischemic heart diseases (AOR: 2.08; 95% CI: 1.37, 3.15), pulmonary and other heart diseases (AOR: 2.13; 95% CI: 1.36, 3.32) and chronic kidney diseases (AOR: 1.81; 95% CI: 1.01, 3.25) had higher odds of severe COVID-19 symptoms. Suffering from multiple co-morbidities increased the odds of developing severe COVID-19 symptoms substantially in comparison to having only one co-morbidity i.e., (AOR: 1.52; 95% CI 1.76–2.60) to (AOR: 2.33; 95% CI: 1.37, 3.97). Identifying these risk factors could assist in the early recognition of high-risk populations and ensure the most appropriate preventive measures and required medical management during the pandemic.
- Open Access
- 29 June 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (7) , 899
The Gradient-Boosting Method for Tackling High Computing Demand in Underwater Acoustic Propagation Modeling
Agent-based models return spatiotemporal information used to process time series of specific parameters for specific individuals called “agents”. For complex, advanced and detailed models, this typically comes at the expense of high computing times and requires access to important computing resources. This paper provides an example on how machine learning and artificial intelligence can help predict an agent-based model’s output values at regular intervals without having to rely on time-consuming numerical calculations. Gradient-boosting XGBoost under GNU package’s R was used in the social-ecological agent-based model 3MTSim to interpolate, in the time domain, sound pressure levels received at the agents’ positions that were occupied by the endangered St. Lawrence Estuary and Saguenay Fjord belugas and caused by anthropomorphic noise of nearby transiting merchant vessels. A mean error of 3.23 ± 3.76(1) dB on received sound pressure levels was predicted when compared to ground truth values that were processed using rigorous, although time-consuming, numerical algorithms. The computing time gain was significant, i.e., it was estimated to be 10-fold higher than the ground truth simulation, whilst maintaining the original temporal resolution.- 29 June 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (7) , 899
Open AccessThe Gradient-Boosting Method for Tackling High Computing Demand in Underwater Acoustic Propagation Modeling
Agent-based models return spatiotemporal information used to process time series of specific parameters for specific individuals called “agents”. For complex, advanced and detailed models, this typically comes at the expense of high computing times and requires access to important computing resources. This paper provides an example on how machine learning and artificial intelligence can help predict an agent-based model’s output values at regular intervals without having to rely on time-consuming numerical calculations. Gradient-boosting XGBoost under GNU package’s R was used in the social-ecological agent-based model 3MTSim to interpolate, in the time domain, sound pressure levels received at the agents’ positions that were occupied by the endangered St. Lawrence Estuary and Saguenay Fjord belugas and caused by anthropomorphic noise of nearby transiting merchant vessels. A mean error of 3.23 ± 3.76(1) dB on received sound pressure levels was predicted when compared to ground truth values that were processed using rigorous, although time-consuming, numerical algorithms. The computing time gain was significant, i.e., it was estimated to be 10-fold higher than the ground truth simulation, whilst maintaining the original temporal resolution.