Search

Climate change significantly impacts public health, driving the emergence and spread of epidemics. Climate health models are essential for assessing and predicting disease outbreaks influenced by climatic variables like temperature and precipitation. For instance, dengue and malaria correlate with temperature changes, while cholera is linked to precipitation anomalies. Advances in AI-enabled weather prediction (AI-NWP) have improved forecasting, but integrating climate models with health systems is hindered by the lack of comprehensive, granular health datasets. This study introduces EpiClim: India's Epidemic-Climate Dataset, the first weekly district-wise dataset for major epidemics in India from 2009 to the present, sourced from the Integrated Disease Surveillance Programme (IDSP). The dataset, covering diseases like dengue, malaria, and acute-diarrheal disease, bridges the gap between climate and health data, enabling the integration of climate forecasts with epidemic prediction models. This work lays the foundation for coupling predictive climate health models with weather and climate models, advancing efforts to mitigate climate-induced public health crises.

This research paper delves into the development of an Optical Character Recognition (OCR) system for the recognition of Ashokan Brahmi characters using Convolutional Neural Networks. It utilizes a comprehensive dataset of character images to train the models, along with data augmentation techniques to optimize the training process. Furthermore, the paper incorporates image preprocessing to remove noise, as well as image segmentation to facilitate line and character segmentation. The study mainly focuses on three pre-trained CNNs, namely LeNet, VGG-16, and MobileNet and compares their accuracy. Transfer learning was employed to adapt the pre-trained models to the Ashokan Brahmi character dataset. The findings reveal that MobileNet outperforms the other two models in terms of accuracy, achieving a validation accuracy of 95.94% and validation loss of 0.129. The paper provides an in-depth analysis of the implementation process using MobileNet and discusses the implications of the findings. The use of OCR for character recognition is of significant importance in the field of epigraphy, specifically for the preservation and digitization of ancient scripts. The results of this research paper demonstrate the effectiveness of using pre-trained CNNs for the recognition of Ashokan Brahmi characters.

Efficiently exploring complex loss landscapes is key to the performance of deep neural networks. While momentum-based optimizers are widely used in state-of-the-art setups, classical momentum can still struggle with large, misaligned gradients, leading to oscillations. To address this, we propose Torque-Aware Momentum (TAM), which introduces a damping factor based on the angle between the new gradients and previous momentum, stabilizing the update direction during training. Empirical results show that TAM, which can be combined with both SGD and Adam, enhances exploration, handles distribution shifts more effectively, and improves generalization performance across various tasks, including image classification and large language model fine-tuning, when compared to classical momentum-based optimizers.

Regulatory documents are rich in nuanced terminology and specialized semantics. FRAG systems: Frozen retrieval-augmented generators utilizing pre-trained (or, frozen) components face consequent challenges with both retriever and answering performance. We present a system that adapts the retriever performance to the target domain using a multi-stage tuning (MST) strategy. Our retrieval approach, called MST-R (a) first fine-tunes encoders used in vector stores using hard negative mining, (b) then uses a hybrid retriever, combining sparse and dense retrievers using reciprocal rank fusion, and then (c) adapts the cross-attention encoder by fine-tuning only the top-k retrieved results. We benchmark the system performance on the dataset released for the RIRAG challenge (as part of the RegNLP workshop at COLING 2025). We achieve significant performance gains obtaining a top rank on the RegNLP challenge leaderboard. We also show that a trivial answering approach games the RePASs metric outscoring all baselines and a pre-trained Llama model. Analyzing this anomaly, we present important takeaways for future research.

In this work, we compare the performance of deep learning models for classifying the spinodal dataset. We evaluate state-of-the-art models (MobileViT, NAT, EfficientNet, CNN), alongside several ensemble models (majority voting, AdaBoost). Additionally, we explore the dataset in a transformed color space. Our findings show that NAT and MobileViT outperform other models, achieving the highest metrics-accuracy, AUC, and F1 score on both training and testing data (NAT: 94.65, 0.98, 0.94; MobileViT: 94.20, 0.98, 0.94), surpassing the earlier CNN model (88.44, 0.95, 0.88). We also discuss failure cases for the top performing models.

The optimal model for a given task is often challenging to determine, requiring training multiple models from scratch which becomes prohibitive as dataset and model sizes grow. A more efficient alternative is to reuse smaller pre-trained models by expanding them, however, this is not widely adopted as how this impacts training dynamics remains poorly understood. While prior works have introduced statistics to measure these effects, they remain flawed. To rectify this, we offer a new approach for understanding and quantifying the impact of expansion through the lens of the loss landscape, which has been shown to contain a manifold of linearly connected minima. Building on this new perspective, we propose a metric to study the impact of expansion by estimating the size of the manifold. Experimental results show a clear relationship between gains in performance and manifold size, enabling the comparison of candidate models and presenting a first step towards expanding models more reliably based on geometric properties of the loss landscape.

Accurate obstacle identification represents a fundamental challenge within the scope of near-field perception for autonomous driving. Conventionally, fisheye cameras are frequently employed for comprehensive surround-view perception, including rear-view obstacle localization. However, the performance of such cameras can significantly deteriorate in low-light conditions, during nighttime, or when subjected to intense sun glare. Conversely, cost-effective sensors like ultrasonic sensors remain largely unaffected under these conditions. Therefore, we present, to our knowledge, the first end-to-end multimodal fusion model tailored for efficient obstacle perception in a bird's-eye-view (BEV) perspective, utilizing fisheye cameras and ultrasonic sensors. Initially, ResNeXt-50 is employed as a set of unimodal encoders to extract features specific to each modality. Subsequently, the feature space associated with the visible spectrum undergoes transformation into BEV. The fusion of these two modalities is facilitated via concatenation. At the same time, the ultrasonic spectrum-based unimodal feature maps pass through content-aware dilated convolution, applied to mitigate the sensor misalignment between two sensors in the fused feature space. Finally, the fused features are utilized by a two-stage semantic occupancy decoder to generate grid-wise predictions for precise obstacle perception. We conduct a systematic investigation to determine the optimal strategy for multimodal fusion of both sensors. We provide insights into our dataset creation procedures, annotation guidelines, and perform a thorough data analysis to ensure adequate coverage of all scenarios. When applied to our dataset, the experimental results underscore the robustness and effectiveness of our proposed multimodal fusion approach., Comment: 16 pages, 12 Figures, 6 tables

The proliferation of open-source scientific software for science and research presents opportunities and challenges. In this paper, we introduce the SciCat dataset -- a comprehensive collection of Free-Libre Open Source Software (FLOSS) projects, designed to address the need for a curated repository of scientific and research software. This collection is crucial for understanding the creation of scientific software and aiding in its development. To ensure extensive coverage, our approach involves selecting projects from a pool of 131 million deforked repositories from the World of Code data source. Subsequently, we analyze README.md files using OpenAI's advanced language models. Our classification focuses on software designed for scientific purposes, research-related projects, and research support software. The SciCat dataset aims to become an invaluable tool for researching science-related software, shedding light on emerging trends, prevalent practices, and challenges in the field of scientific software development. Furthermore, it includes data that can be linked to the World of Code, GitHub, and other platforms, providing a solid foundation for conducting comparative studies between scientific and non-scientific software.

Computational and data-enabled science and engineering are revolutionizing advances throughout science and society, at all scales of computing. For example, teams in the U.S. DOE Exascale Computing Project have been tackling new frontiers in modeling, simulation, and analysis by exploiting unprecedented exascale computing capabilities-building an advanced software ecosystem that supports next-generation applications and addresses disruptive changes in computer architectures. However, concerns are growing about the productivity of the developers of scientific software, its sustainability, and the trustworthiness of the results that it produces. Members of the IDEAS project serve as catalysts to address these challenges through fostering software communities, incubating and curating methodologies and resources, and disseminating knowledge to advance developer productivity and software sustainability. This paper discusses how these synergistic activities are advancing scientific discovery-mitigating technical risks by building a firmer foundation for reproducible, sustainable science at all scales of computing, from laptops to clusters to exascale and beyond., Comment: 12 pages, 1 figure

Research software plays a crucial role in advancing scientific knowledge, but ensuring its sustainability, maintainability, and long-term viability is an ongoing challenge. The Sustainable Research Software Institute (SRSI) Model has been designed to address the concerns, and presents a comprehensive framework designed to promote sustainable practices in the research software community. However the SRSI Model does not address the transitional requirements for the Exascale Computing Project (ECP) Software Technology (ECP-ST) focus area specifically. This white paper provides an overview and detailed description of how ECP-ST will transition into the SRSI in a compressed time frame that a) meets the needs of the ECP end-of-technical-activities deadline; and b) ensures the continuity of the sustainability efforts that are already underway., Comment: 7 pages, 1 figure

Research software plays a crucial role in advancing scientific knowledge, but ensuring its sustainability, maintainability, and long-term viability is an ongoing challenge. To address these concerns, the Sustainable Research Software Institute (SRSI) Model presents a comprehensive framework designed to promote sustainable practices in the research software community. This white paper provides an in-depth overview of the SRSI Model, outlining its objectives, services, funding mechanisms, collaborations, and the significant potential impact it could have on the research software community. It explores the wide range of services offered, diverse funding sources, extensive collaboration opportunities, and the transformative influence of the SRSI Model on the research software landscape, Comment: 13 pages, 1 figure

Sharpness-aware minimization (SAM) methods have gained increasing popularity by formulating the problem of minimizing both loss value and loss sharpness as a minimax objective. In this work, we increase the efficiency of the maximization and minimization parts of SAM's objective to achieve a better loss-sharpness trade-off. By taking inspiration from the Lookahead optimizer, which uses multiple descent steps ahead, we propose Lookbehind, which performs multiple ascent steps behind to enhance the maximization step of SAM and find a worst-case perturbation with higher loss. Then, to mitigate the variance in the descent step arising from the gathered gradients across the multiple ascent steps, we employ linear interpolation to refine the minimization step. Lookbehind leads to a myriad of benefits across a variety of tasks. Particularly, we show increased generalization performance, greater robustness against noisy weights, as well as improved learning and less catastrophic forgetting in lifelong learning settings. Our code is available at https://github.com/chandar-lab/Lookbehind-SAM., Comment: ICML 2024

Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergence and robustness to hyperparameter settings. However, they often struggle with generalization, attributed to their tendency to converge to sharp minima in the loss landscape. To address this, we propose a new memory-augmented version of Adam that encourages exploration towards flatter minima by incorporating a buffer of critical momentum terms during training. This buffer prompts the optimizer to overshoot beyond narrow minima, promoting exploration. Through comprehensive analysis in simple settings, we illustrate the efficacy of our approach in increasing exploration and bias towards flatter minima. We empirically demonstrate that it can improve model performance for image classification on ImageNet and CIFAR10/100, language modelling on Penn Treebank, and online learning tasks on TinyImageNet and 5-dataset. Our code is available at \url{https://github.com/chandar-lab/CMOptimizer}., Comment: Published in Transactions on Machine Learning Research

Callaway's simplified heat flow model is often used to confirm experimental realizations of unconventional, hydrodynamic and Poiseuille phonon transport in ultrahigh thermal conductivity ($\kappa$) materials, due to its simplicity and low computational cost. Here, we show that the Callaway model works exceptionally well for most ultrahigh-$\kappa$ materials like diamond and boron nitride, but fails dramatically for boron arsenide (BAs) and boron antimonide (BSb). This failure is driven by the inability of the Callaway model to effectively describe the severely restricted phonon scattering in BAs and BSb, where many scattering selection rules are activated simultaneously. Our work highlights the powerful predictive capability of the Callaway model, and gives insights into the nature of phonon scattering in ultrahigh-$\kappa$ materials and the suitability of the Callaway's description of heat flow through them.

Cognitive psychology delves on understanding perception, attention, memory, language, problem-solving, decision-making, and reasoning. Large language models (LLMs) are emerging as potent tools increasingly capable of performing human-level tasks. The recent development in the form of GPT-4 and its demonstrated success in tasks complex to humans exam and complex problems has led to an increased confidence in the LLMs to become perfect instruments of intelligence. Although GPT-4 report has shown performance on some cognitive psychology tasks, a comprehensive assessment of GPT-4, via the existing well-established datasets is required. In this study, we focus on the evaluation of GPT-4's performance on a set of cognitive psychology datasets such as CommonsenseQA, SuperGLUE, MATH and HANS. In doing so, we understand how GPT-4 processes and integrates cognitive psychology with contextual information, providing insight into the underlying cognitive processes that enable its ability to generate the responses. We show that GPT-4 exhibits a high level of accuracy in cognitive psychology tasks relative to the prior state-of-the-art models. Our results strengthen the already available assessments and confidence on GPT-4's cognitive psychology abilities. It has significant potential to revolutionize the field of AI, by enabling machines to bridge the gap between human and machine reasoning.

The Better Scientific Software Fellowship (BSSwF) was launched in 2018 to foster and promote practices, processes, and tools to improve developer productivity and software sustainability of scientific codes. BSSwF's vision is to grow the community with practitioners, leaders, mentors, and consultants to increase the visibility of scientific software production and sustainability. Over the last five years, many fellowship recipients and honorable mentions have identified as research software engineers (RSEs). This paper provides case studies from several of the program's participants to illustrate some of the diverse ways BSSwF has benefited both the RSE and scientific communities. In an environment where the contributions of RSEs are too often undervalued, we believe that programs such as BSSwF can be a valuable means to recognize and encourage community members to step outside of their regular commitments and expand on their work, collaborations and ideas for a larger audience., Comment: submitted to Computing in Science & Engineering (CiSE), Special Issue on the Future of Research Software Engineers in the US

Many studies on scaling laws consider basic factors such as model size, model shape, dataset size, and compute power. These factors are easily tunable and represent the fundamental elements of any machine learning setup. But researchers have also employed more complex factors to estimate the test error and generalization performance with high predictability. These factors are generally specific to the domain or application. For example, feature diversity was primarily used for promoting syn-to-real transfer by Chen et al. (2021). With numerous scaling factors defined in previous works, it would be interesting to investigate how these factors may affect overall generalization performance in the context of self-supervised learning with CNN models. How do individual factors promote generalization, which includes varying depth, width, or the number of training epochs with early stopping? For example, does higher feature diversity result in higher accuracy held in complex settings other than a syn-to-real transfer? How do these factors depend on each other? We found that the last layer is the most diversified throughout the training. However, while the model's test error decreases with increasing epochs, its diversity drops. We also discovered that diversity is directly related to model width., Comment: Accepted at 1st Conference on Lifelong Learning Agents, 2022 - Workshop Track

This primer is an attempt to provide a detailed summary of the different facets of lifelong learning. We start with Chapter 2 which provides a high-level overview of lifelong learning systems. In this chapter, we discuss prominent scenarios in lifelong learning (Section 2.4), provide 8 Introduction a high-level organization of different lifelong learning approaches (Section 2.5), enumerate the desiderata for an ideal lifelong learning system (Section 2.6), discuss how lifelong learning is related to other learning paradigms (Section 2.7), describe common metrics used to evaluate lifelong learning systems (Section 2.8). This chapter is more useful for readers who are new to lifelong learning and want to get introduced to the field without focusing on specific approaches or benchmarks. The remaining chapters focus on specific aspects (either learning algorithms or benchmarks) and are more useful for readers who are looking for specific approaches or benchmarks. Chapter 3 focuses on regularization-based approaches that do not assume access to any data from previous tasks. Chapter 4 discusses memory-based approaches that typically use a replay buffer or an episodic memory to save subset of data across different tasks. Chapter 5 focuses on different architecture families (and their instantiations) that have been proposed for training lifelong learning systems. Following these different classes of learning algorithms, we discuss the commonly used evaluation benchmarks and metrics for lifelong learning (Chapter 6) and wrap up with a discussion of future challenges and important research directions in Chapter 7., Comment: Lifelong Learning Primer

Placement of sensors on vehicles for safety and autonomous capability is a complex optimization problem when considered in the full-blown form, with different constraints. Considering that Quantum Computers are expected to be able to solve certain optimization problems more "easily" in the future, the problem was posted as part of the BMW Quantum Computing Challenge 2021. In this paper, we have presented two formulations for quantum-enhanced solutions in a systematic manner. In the process, necessary simplifications are invoked to accommodate the current capabilities of Quantum Simulators and Hardware. The presented results and observations from elaborate simulation studies demonstrate the correct functionality and usefulness of the proposals., Comment: 7 pages, 5 figures

In the search for a sustainable approach for software ecosystems that supports experimental and observational science (EOS) across Oak Ridge National Laboratory (ORNL), we conducted a survey to understand the current and future landscape of EOS software and data. This paper describes the survey design we used to identify significant areas of interest, gaps, and potential opportunities, followed by a discussion on the obtained responses. The survey formulates questions about project demographics, technical approach, and skills required for the present and the next five years. The study was conducted among 38 ORNL participants between June and July of 2021 and followed the required guidelines for human subjects training. We plan to use the collected information to help guide a vision for sustainable, community-based, and reusable scientific software ecosystems that need to adapt effectively to: i) the evolving landscape of heterogeneous hardware in the next generation of instruments and computing (e.g. edge, distributed, accelerators), and ii) data management requirements for data-driven science using artificial intelligence., Comment: 14 pages, no figures, only tables