Climate models are biased with respect to real world observations and usually need to be calibrated prior to impact studies. The suite of statistical methods that enable such calibrations is called bias correction (BC). However, current BC methods struggle to adjust for temporal biases, because they disregard the dependence between consecutive time-points. As a result, climate statistics with long-range temporal properties, such as heatwave duration and frequency, cannot be corrected accurately, making it more difficult to produce reliable impact studies on such climate statistics. In this paper, we offer a novel BC methodology to correct for temporal biases. This is made possible by i) re-thinking BC as a probability model rather than an algorithmic procedure, and ii) adapting state-of-the-art machine-learning (ML) probabilistic attention models to fit the BC task. With a case study of heatwave duration statistics in Abuja, Nigeria, and Tokyo, Japan, we show striking results compared to current climate model outputs and alternative BC methods.
相關內容
Defect detection is one of the most important yet challenging tasks in the quality control stage in the manufacturing sector. In this work, we introduce a Tensor Convolutional Neural Network (T-CNN) and examine its performance on a real defect detection application in one of the components of the ultrasonic sensors produced at Robert Bosch's manufacturing plants. Our quantum-inspired T-CNN operates on a reduced model parameter space to substantially improve the training speed and performance of an equivalent CNN model without sacrificing accuracy. More specifically, we demonstrate how T-CNNs are able to reach the same performance as classical CNNs as measured by quality metrics, with up to fifteen times fewer parameters and 4% to 19% faster training times. Our results demonstrate that the T-CNN greatly outperforms the results of traditional human visual inspection, providing value in a current real application in manufacturing.
With the rapid increase in machine learning workloads performed on HPC systems, it is beneficial to regularly perform machine learning specific benchmarks to monitor performance and identify issues. Furthermore, as part of the Edinburgh International Data Facility, EPCC currently hosts a wide range of machine learning accelerators including Nvidia GPUs, the Graphcore Bow Pod64 and Cerebras CS-2, which are managed via Kubernetes and Slurm. We extended the Reframe framework to support the Kubernetes scheduler backend, and utilise Reframe to perform machine learning benchmarks, and we discuss the preliminary results collected and challenges involved in integrating Reframe across multiple platforms and architectures.
Reliability is an important quantification of measurement precision based on a latent variable measurement model. Inspired by McDonald (2011), we present a regression framework of reliability, placing emphasis on whether latent or observed scores serve as the regression outcome. Our theory unifies two extant perspectives of reliability: (a) classical test theory (measurement decomposition), and (b) optimal prediction of latent scores (prediction decomposition). Importantly, reliability should be treated as a property of the observed score under a measurement decomposition, but a property of the latent score under a prediction decomposition. To facilitate the evaluation and interpretation of distinct reliability coefficients for complex measurement models, we introduce a Monte Carlo approach for approximate calculation of reliability. We illustrate the proposed computational procedure with an empirical data analysis, which concerns measuring susceptibility and severity of depressive symptoms using a two-dimensional item response theory model. We conclude with a discussion on computing reliability coefficients and outline future avenues of research.
Empirical quantiles for finitely distributed univariate random variables can be obtained by solving a certain linear program. It is shown in this short note that multivariate empirical quantiles can be obtained in a very similar way by solving a vector linear program. This connection provides a new approach for computing Tukey depth regions and more general cone quantile sets.
Beyond improving trust and validating model fairness, xAI practices also have the potential to recover valuable scientific insights in application domains where little to no prior human intuition exists. To that end, we propose a method to extract global concept explanations from the predictions of graph neural networks to develop a deeper understanding of the tasks underlying structure-property relationships. We identify concept explanations as dense clusters in the self-explaining Megan models subgraph latent space. For each concept, we optimize a representative prototype graph and optionally use GPT-4 to provide hypotheses about why each structure has a certain effect on the prediction. We conduct computational experiments on synthetic and real-world graph property prediction tasks. For the synthetic tasks we find that our method correctly reproduces the structural rules by which they were created. For real-world molecular property regression and classification tasks, we find that our method rediscovers established rules of thumb. More specifically, our results for molecular mutagenicity prediction indicate more fine-grained resolution of structural details than existing explainability methods, consistent with previous results from chemistry literature. Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.
We propose an autoregressive framework for modelling dynamic networks with dependent edges. It encompasses the models which accommodate, for example, transitivity, density-dependent and other stylized features often observed in real network data. By assuming the edges of network at each time are independent conditionally on their lagged values, the models, which exhibit a close connection with temporal ERGMs, facilitate both simulation and the maximum likelihood estimation in the straightforward manner. Due to the possible large number of parameters in the models, the initial MLEs may suffer from slow convergence rates. An improved estimator for each component parameter is proposed based on an iteration based on the projection which mitigates the impact of the other parameters (Chang et al., 2021, 2023). Based on a martingale difference structure, the asymptotic distribution of the improved estimator is derived without the stationarity assumption. The limiting distribution is not normal in general, and it reduces to normal when the underlying process satisfies some mixing conditions. Illustration with a transitivity model was carried out in both simulation and a real network data set.
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing concern in the current era. This paper provides a comprehensive review of recent advances in aligning LLMs with the ever-changing world knowledge without re-training from scratch. We categorize research works systemically and provide in-depth comparisons and discussion. We also discuss existing challenges and highlight future directions to facilitate research in this field. We release the paper list at //github.com/hyintell/awesome-refreshing-llms
The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be alleviated if we could partially predict a network's trained accuracy from its initial state. In this work, we examine the overlap of activations between datapoints in untrained networks and motivate how this can give a measure which is usefully indicative of a network's trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU, and verify its effectiveness on NAS-Bench-101, NAS-Bench-201, NATS-Bench, and Network Design Spaces. Our approach can be readily combined with more expensive search methods; we examine a simple adaptation of regularised evolutionary search. Code for reproducing our experiments is available at //github.com/BayesWatch/nas-without-training.
Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE. However, N-1, 1-N and N-N predictions still remain challenging. In this work, we propose a novel translational distance-based approach for knowledge graph link prediction. The proposed method includes two-folds, first we extend the RotatE from 2D complex domain to high dimension space with orthogonal transforms to model relations for better modeling capacity. Second, the graph context is explicitly modeled via two directed context representations. These context representations are used as part of the distance scoring function to measure the plausibility of the triples during training and inference. The proposed approach effectively improves prediction accuracy on the difficult N-1, 1-N and N-N cases for knowledge graph link prediction task. The experimental results show that it achieves better performance on two benchmark data sets compared to the baseline RotatE, especially on data set (FB15k-237) with many high in-degree connection nodes.
Automatically creating the description of an image using any natural languages sentence like English is a very challenging task. It requires expertise of both image processing as well as natural language processing. This paper discuss about different available models for image captioning task. We have also discussed about how the advancement in the task of object recognition and machine translation has greatly improved the performance of image captioning model in recent years. In addition to that we have discussed how this model can be implemented. In the end, we have also evaluated the performance of model using standard evaluation matrices.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191