arXiv subjects

Abhishek Sharma

Publications and source records attributed to Abhishek Sharma.

At least 55 records · Page 3Linked to original sources

arXiv2025

Temporal Reasoning in AI systems

Commonsense temporal reasoning at scale is a core problem for cognitive systems. The correct inference of the duration for which fluents hold is required by many tasks, including natural language understanding and planning. Many AI systems have limited deductive closure because they cannot extrapolate information correctly regarding existing fluents and events. In this study, we discuss the knowledge representation and reasoning schemes required for robust temporal projection in the Cyc Knowledge Base. We discuss how events can start and end risk periods for fluents. We then use discrete survival functions, which represent knowledge of the persistence of facts, to extrapolate a given fluent. The extrapolated intervals can be truncated by temporal constraints and other types of commonsense knowledge. Finally, we present the results of experiments to demonstrate that these methods obtain significant improvements in terms of Q/A performance.

cs.AI↗

arXiv2025

Growth Patterns of Inference

What properties of a first-order search space support/hinder inference? What kinds of facts would be most effective to learn? Answering these questions is essential for understanding the dynamics of deductive reasoning and creating large-scale knowledge-based learning systems that support efficient inference. We address these questions by developing a model of how the distribution of ground facts affects inference performance in search spaces. Experiments suggest that uniform search spaces are suitable for larger KBs whereas search spaces with skewed degree distribution show better performance in smaller KBs. A sharp transition in Q/A performance is seen in some cases, suggesting that analysis of the structure of search spaces with existing knowledge should be used to guide the acquisition of new ground facts in learning systems.

cs.AI↗

arXiv2025

A Coordination-based Approach for Focused Learning in Knowledge-Based Systems

Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for these knowledge-based systems which would lead to maximum Q/A performance. To understand the dynamics of this problem, we simulate the properties of a learning strategy, which sends learning requests to an external knowledge source. We show that choosing an optimal set of facts for these learning systems is similar to a coordination game, and use reinforcement learning to solve this problem. Experiments show that such an approach can significantly improve Q/A performance.

cs.AI↗

arXiv2024

Advancing Parkinson's Disease Progression Prediction: Comparing Long Short-Term Memory Networks and Kolmogorov-Arnold Networks

Parkinson's Disease (PD) is a degenerative neurological disorder that impairs motor and non-motor functions, significantly reducing quality of life and increasing mortality risk. Early and accurate detection of PD progression is vital for effective management and improved patient outcomes. Current diagnostic methods, however, are often costly, time-consuming, and require specialized equipment and expertise. This work proposes an innovative approach to predicting PD progression using regression methods, Long Short-Term Memory (LSTM) networks, and Kolmogorov Arnold Networks (KAN). KAN, utilizing spline-parametrized univariate functions, allows for dynamic learning of activation patterns, unlike traditional linear models. The Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is a comprehensive tool for evaluating PD symptoms and is commonly used to measure disease progression. Additionally, protein or peptide abnormalities are linked to PD onset and progression. Identifying these associations can aid in predicting disease progression and understanding molecular changes. Comparing multiple models, including LSTM and KAN, this study aims to identify the method that delivers the highest metrics. The analysis reveals that KAN, with its dynamic learning capabilities, outperforms other approaches in predicting PD progression. This research highlights the potential of AI and machine learning in healthcare, paving the way for advanced computational models to enhance clinical predictions and improve patient care and treatment strategies in PD management.

cs.LG↗

arXiv2024

Automated Patient Positioning with Learned 3D Hand Gestures

Positioning patients for scanning and interventional procedures is a critical task that requires high precision and accuracy. The conventional workflow involves manually adjusting the patient support to align the center of the target body part with the laser projector or other guiding devices. This process is not only time-consuming but also prone to inaccuracies. In this work, we propose an automated patient positioning system that utilizes a camera to detect specific hand gestures from technicians, allowing users to indicate the target patient region to the system and initiate automated positioning. Our approach relies on a novel multi-stage pipeline to recognize and interpret the technicians' gestures, translating them into precise motions of medical devices. We evaluate our proposed pipeline during actual MRI scanning procedures, using RGB-Depth cameras to capture the process. Results show that our system achieves accurate and precise patient positioning with minimal technician intervention. Furthermore, we validate our method on HaGRID, a large-scale hand gesture dataset, demonstrating its effectiveness in hand detection and gesture recognition.

cs.CV↗

arXiv2024

Measuring the ATLAS ITk Pixel Detector Material via Multiple Scattering of Positrons at the CERN PS

The ITk is a new silicon tracker for the ATLAS experiment designed to increase detector resolution, readout capacity, and radiation hardness, in preparation for the larger number of simultaneous proton-proton interactions at the High Luminosity LHC. This paper presents the first direct measurement of the material budget of an ATLAS ITk pixel module, performed at a testbeam at the CERN Proton Synchrotron via the multiple scattering of low energy positrons within the module volume. Using a four plane telescope of thin monolithic pixel detectors from the MALTA collaboration, scattering datasets were recorded at a beam energy of $1.2\,\text{GeV}$. Kink angle distributions were extracted from tracks derived with and without information from the ITk pixel module, and were fit to extract the RMS scattering angle, which was converted to a fractional radiation length $x/X_0$. The average $x/X_0$ across the module was measured as $[0.89 \pm 0.01 \text{ (resolution)} \pm 0.01 \text{ (subtraction)} \pm 0.08 \text{ (beam momentum band)}]\%$, which agrees within uncertainties with an estimate of $0.88\%$ derived from material component expectations.

physics.ins-det↗

arXiv2024

Decision-Focused Model-based Reinforcement Learning for Reward Transfer

Model-based reinforcement learning (MBRL) provides a way to learn a transition model of the environment, which can then be used to plan personalized policies for different patient cohorts and to understand the dynamics involved in the decision-making process. However, standard MBRL algorithms are either sensitive to changes in the reward function or achieve suboptimal performance on the task when the transition model is restricted. Motivated by the need to use simple and interpretable models in critical domains such as healthcare, we propose a novel robust decision-focused (RDF) algorithm that learns a transition model that achieves high returns while being robust to changes in the reward function. We demonstrate our RDF algorithm can be used with several model classes and planning algorithms. We also provide theoretical and empirical evidence, on a variety of simulators and real patient data, that RDF can learn simple yet effective models that can be used to plan personalized policies.

cs.LG↗

arXiv2024

Deep Learning for Fetal Inflammatory Response Diagnosis in the Umbilical Cord

Inflammation of the umbilical cord can be seen as a result of ascending intrauterine infection or other inflammatory stimuli. Acute fetal inflammatory response (FIR) is characterized by infiltration of the umbilical cord by fetal neutrophils, and can be associated with neonatal sepsis or fetal inflammatory response syndrome. Recent advances in deep learning in digital pathology have demonstrated favorable performance across a wide range of clinical tasks, such as diagnosis and prognosis. In this study we classified FIR from whole slide images (WSI). We digitized 4100 histological slides of umbilical cord stained with hematoxylin and eosin(H&E) and extracted placental diagnoses from the electronic health record. We build models using attention-based whole slide learning models. We compared strategies between features extracted by a model (ConvNeXtXLarge) pretrained on non-medical images (ImageNet), and one pretrained using histopathology images (UNI). We trained multiple iterations of each model and combined them into an ensemble. The predictions from the ensemble of models trained using UNI achieved an overall balanced accuracy of 0.836 on the test dataset. In comparison, the ensembled predictions using ConvNeXtXLarge had a lower balanced accuracy of 0.7209. Heatmaps generated from top accuracy model appropriately highlighted arteritis in cases of FIR 2. In FIR 1, the highest performing model assigned high attention to areas of activated-appearing stroma in Wharton's Jelly. However, other high-performing models assigned attention to umbilical vessels. We developed models for diagnosis of FIR from placental histology images, helping reduce interobserver variability among pathologists. Future work may examine the utility of these models for identifying infants at risk of systemic inflammatory response or early onset neonatal sepsis.

eess.IV↗

arXiv2024

Machine learning identification of maternal inflammatory response and histologic choroamnionitis from placental membrane whole slide images

The placenta forms a critical barrier to infection through pregnancy, labor and, delivery. Inflammatory processes in the placenta have short-term, and long-term consequences for offspring health. Digital pathology and machine learning can play an important role in understanding placental inflammation, and there have been very few investigations into methods for predicting and understanding Maternal Inflammatory Response (MIR). This work intends to investigate the potential of using machine learning to understand MIR based on whole slide images (WSI), and establish early benchmarks. To that end, we use Multiple Instance Learning framework with 3 feature extractors: ImageNet-based EfficientNet-v2s, and 2 histopathology foundation models, UNI and Phikon to investigate predictability of MIR stage from histopathology WSIs. We also interpret predictions from these models using the learned attention maps from these models. We also use the MIL framework for predicting white blood cells count (WBC) and maximum fever temperature ($T_{max}$). Attention-based MIL models are able to classify MIR with a balanced accuracy of up to 88.5% with a Cohen's Kappa ($κ$) of up to 0.772. Furthermore, we found that the pathology foundation models (UNI and Phikon) are both able to achieve higher performance with balanced accuracy and $κ$, compared to ImageNet-based feature extractor (EfficientNet-v2s). For WBC and $T_{max}$ prediction, we found mild correlation between actual values and those predicted from histopathology WSIs. We used MIL framework for predicting MIR stage from WSIs, and compared effectiveness of foundation models as feature extractors, with that of an ImageNet-based model. We further investigated model failure cases and found them to be either edge cases prone to interobserver variability, examples of pathologist's overreach, or mislabeled due to processing errors.

cs.CV↗

arXiv2024

Decision-Point Guided Safe Policy Improvement

Within batch reinforcement learning, safe policy improvement (SPI) seeks to ensure that the learnt policy performs at least as well as the behavior policy that generated the dataset. The core challenge in SPI is seeking improvements while balancing risk when many state-action pairs may be infrequently visited. In this work, we introduce Decision Points RL (DPRL), an algorithm that restricts the set of state-action pairs (or regions for continuous states) considered for improvement. DPRL ensures high-confidence improvement in densely visited states (i.e. decision points) while still utilizing data from sparsely visited states. By appropriately limiting where and how we may deviate from the behavior policy, we achieve tighter bounds than prior work; specifically, our data-dependent bounds do not scale with the size of the state and action spaces. In addition to the analysis, we demonstrate that DPRL is both safe and performant on synthetic and real datasets.

cs.LG↗

arXiv2024

Mapping Evolution of Molecules Across Biochemistry with Assembly Theory

Evolution is often understood through genetic mutations driving changes in an organism's fitness, but there is potential to extend this understanding beyond the genetic code. We propose that natural products - complex molecules central to Earth's biochemistry can be used to uncover evolutionary mechanisms beyond genes. By applying Assembly Theory (AT), which views selection as a process not limited to biological systems, we can map and measure evolutionary forces in these molecules. AT enables the exploration of the assembly space of natural products, demonstrating how the principles of the selfish gene apply to these complex chemical structures, selecting vastly improbable and complex molecules from a vast space of possibilities. By comparing natural products with a broader molecular database, we can assess the degree of evolutionary contingency, providing insight into how molecular novelty emerges and persists. This approach not only quantifies evolutionary selection at the molecular level but also offers a new avenue for drug discovery by exploring the molecular assembly spaces of natural products. Our method provides a fresh perspective on measuring the evolutionary processes both, shaping and being read out, by the molecular imprint of selection.

q-bio.PE↗

arXiv2024

AI-Driven Robotic Crystal Explorer for Rapid Polymorph Identification

Crystallisation is an important phenomenon which facilitates the purification as well as structural and bulk phase material characterisation using crystallographic methods. However, different conditions can lead to a vast set of different crystal structure polymorphs and these often exhibit different physical properties, allowing materials to be tailored to specific purposes. This means the high dimensionality that can result from variations in the conditions which affect crystallisation, and the interaction between them, means that exhaustive exploration is difficult, time-consuming, and costly to explore. Herein we present a robotic crystal search engine for the automated and efficient high-throughput approach to the exploration of crystallisation conditions. The system comprises a closed-loop computer crystal-vision system that uses machine learning to both identify crystals and classify their identity in a multiplexed robotic platform. By exploring the formation of a well-known polymorph, we were able to show how a robotic system could be used to efficiently search experimental space as a function of relative polymorph amount and efficiently create a high dimensionality phase diagram with minimal experimental budget and without expensive analytical techniques such as crystallography. In this way, we identify the set of polymorphs possible within a set of experimental conditions, as well as the optimal values of these conditions to grow each polymorph.

cs.RO↗

arXiv2024

A Comprehensive Convolutional Neural Network Architecture Design using Magnetic Skyrmion and Domain Wall

Spintronic-based neuromorphic hardware offers high-density and rapid data processing at nanoscale lengths by leveraging magnetic configurations like skyrmion and domain walls. Here, we present the maximal hardware implementation of a convolutional neural network (CNN) based on a compact multi-bit skyrmion-based synapse and a hybrid CMOS domain wall-based circuit for activation and max-pooling functionalities. We demonstrate the micromagnetic design and operation of a circular bilayer skyrmion system mimicking a scalable artificial synapse, demonstrated up to 6-bit (64 states) with an ultra-low energy consumption of 0.87 fJ per state update. We further show that the synaptic weight modulation is achieved by the perpendicular current interaction with the labyrinth-maze like uniaxial anisotropy profile, inducing skyrmionic gyration, thereby enabling long-term potentiation (LTP) and long-term depression (LTD) operations. Furthermore, we present a simultaneous rectified linear (ReLU) activation and max pooling circuitry featuring a SOT-based domain wall ReLU with a power consumption of 4.73 $μ$W. The ReLU function, stabilized by a parabolic uniaxial anisotropy profile, encodes domain wall positions into continuous resistance states coupled with the HSPICE circuit simulator. Our integrated skyrmion and domain wall-based spintronic hardware achieves 98.07% accuracy in convolutional neural network (CNN) based pattern recognition task, consuming 110 mW per image.

cond-mat.mes-hall↗

arXiv2024

Phases and correlations in active nematic granular systems

We investigate the statistical behavior of a system comprising fore-aft symmetric rods confined between two vertically vibrating plates using numerical simulations closely resembling the experimental setup studied by Narayan et al., Science 317, 105 (2007). Our focus lies in studying the phase transition of the system from an isotropic phase to a nematic phase as we increase either the rod length or the rod concentration. Our simulations confirm the presence of long-range ordering in the ordered phase. Furthermore, we identify a phase characterized by a periodic ordering profile that disrupts translation symmetry. We also provide a detailed analysis of the translational and rotational diffusive dynamics of the rods. Interestingly, the translational diffusivity of the rods is found to increase with the rod concentration.

cond-mat.soft↗

arXiv2024

Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images

We introduce a novel bottom-up approach for human body mesh reconstruction, specifically designed to address the challenges posed by partial visibility and occlusion in input images. Traditional top-down methods, relying on whole-body parametric models like SMPL, falter when only a small part of the human is visible, as they require visibility of most of the human body for accurate mesh reconstruction. To overcome this limitation, our method employs a "Divide and Fuse (D&F)" strategy, reconstructing human body parts independently before fusing them, thereby ensuring robustness against occlusions. We design Human Part Parametric Models (HPPM) that independently reconstruct the mesh from a few shape and global-location parameters, without inter-part dependency. A specially designed fusion module then seamlessly integrates the reconstructed parts, even when only a few are visible. We harness a large volume of ground-truth SMPL data to train our parametric mesh models. To facilitate the training and evaluation of our method, we have established benchmark datasets featuring images of partially visible humans with HPPM annotations. Our experiments, conducted on these benchmark datasets, demonstrate the effectiveness of our D&F method, particularly in scenarios with substantial invisibility, where traditional approaches struggle to maintain reconstruction quality.

cs.CV↗

arXiv2024

Domain wall and Magnetic Tunnel Junction Hybrid for on-chip Learning in UNet architecture

We present spintronic devices based hardware implementation of UNet for segmentation tasks. Our approach involves designing hardware for convolution, deconvolution, rectified activation function (ReLU), and max pooling layers of the UNet architecture. We designed the convolution and deconvolution layers of the network using the synaptic behavior of the domain wall MTJ. We also construct the ReLU and max pooling functions of the network utilizing the spin hall driven orthogonal current injected MTJ. To incorporate the diverse physics of spin-transport, magnetization dynamics, and CMOS elements in our UNet design, we employ a hybrid simulation setup that couples micromagnetic simulation, non-equilibrium Green's function, SPICE simulation along with network implementation. We evaluate our UNet design on the CamVid dataset and achieve segmentation accuracies of 83.71$\%$ on test data, on par with the software implementation with 821mJ of energy consumption for on-chip training over 150 epochs. We further demonstrate nearly one order $(10\times)$ improvement in the energy requirement of the network using unstable ferromagnet ($Δ$=4.58) over the stable ferromagnet ($Δ$=45) based ReLU and max pooling functions while maintaining the similar accuracy. The hybrid architecture comprising domain wall MTJ and unstable FM-based MTJ leads to an on-chip energy consumption of 85.79mJ during training, with a testing energy cost of 1.55 $μJ$.

cs.ET↗

arXiv2024

Investigation of injector-coupled combustion dynamics in a methane-oxygen combustor using large eddy simulation and dynamic mode decomposition

This paper uses a reactive flow large eddy simulation (LES) and decomposition techniques to study combustion instabilities in a methane-oxygen combustor. This work examines two case scenarios to elucidate the significance of injector-chamber frequency coupling as the cause of thermo-acoustic instability. Initial investigation in a well-known benchmark case of the continuously variable resonance combustor (CVRC) reports the potential instability mechanisms and the role of injector-chamber frequency coupling in thermo-acoustic instability. Subsequently, the multi-element rocket combustor case study identifies the critical resonant modes and highlights potential frequency coupling between the injector and the chamber region. The interplay between longitudinal pressure oscillations in the oxidizer post and transverse pressure waves in the chamber is responsible for the enhanced pressure dynamics in the combustor. The present work uses the dynamic mode decomposition (DMD) technique to reveal the evolution of acoustic modes in injector and chamber for CVRC and multi-element combustor. The dominant pressure mode forms found by DMD analysis also showcase the role of injector-chamber frequency coupling in amplified combustion dynamics. The results demonstrate how the predominant cause of combustion instability in rocket combustors can be effectively determined using the high-fidelity LES framework in conjunction with the modal decomposition technique.

physics.flu-dyn↗

arXiv2024

Template bank to search for exotic gravitational wave signals from astrophysical compact binaries

Modeled searches of gravitational wave signals from compact binary mergers rely on template waveforms determined by the theory of general relativity (GR). Once a signal is detected, one generally performs the model agnostic test of GR, either looking for consistency between the GR waveform and data or introducing phenomenological deviations to detect the departure from GR. The non-trivial presence of beyond-GR physics can alter the waveform and could be missed by the GR template-based searches. A recent study [Phys. Rev. D 107, 024017 (2023)] targeted the binary black hole merger, assuming the parametrized deviation in lower post-Newtonian terms and demonstrated a mild effect on the search sensitivity. Surprisingly, for the search space of binary neutron star (BNS) systems where component masses range from 1 to $2.4\:\rm{M}_\odot$ and parametrized deviations span $1σ$ width of the deviation parameters measured from the GW170817 event, the GR template bank is highly ineffectual for detecting the non-GR signals. Here, we present a new hybrid method to construct a non-GR template bank for the BNS search space. The hybrid method uses the geometric approach of three-dimensional lattice placement to cover most of the parameter space volume, followed by the random method to cover the boundary regions of parameter space. We find that the non-GR bank size is $\sim$15 times larger than the conventional GR bank and is effectual towards detecting non-GR signals in the target search space.

gr-qc↗