Self-attention mechanisms are foundational to Transformer architectures, supporting their impressive success in a wide range of tasks. While there are many self-attention variants, their robustness to noise and spurious correlations has not been well studied. This study evaluates Softmax, Sigmoid, Linear, Doubly Stochastic, and Cosine attention within Vision Transformers under different data corruption scenarios. Through testing across the CIFAR-10, CIFAR-100, and Imagenette datasets, we show that Doubly Stochastic attention is the most robust. It consistently outperformed the next best mechanism by $0.1\%-5.1\%$ when training data, or both training and testing data, were corrupted. Our findings inform self-attention selection in contexts with imperfect data. The code used is available at https://github.com/ctamayor/NeurIPS-Robustness-ViT.

Then we devise a new learning objective based on backdoor adjustment and further harness variational inference to make it tractable for sequence learning problems.

Benchmark data sets are curated collections that enable consistent, reproducible, and objective evaluation of algorithms and models [1, 2]. They are essential for comparing algorithm performance fairly, particularly in machine learning (ML) and artificial intelligence (AI), where the suitability of algorithms can vary widely based on data structure, dimensionality, and distribution [3, 4]. For instance, algorithms that perform exceptionally on structured, tabular data may not generalise well to unstructured image or textual data [5]. Established benchmarks such as ImageNet [2], CIFAR data sets [6], and OpenML benchmarks for structured data [7] have driven innovation by providing clear metrics for progress, fostering reproducibility and trust within the research community [8]. However, in computational sciences, standardised benchmarks remain rare and challenging to establish due to the intrinsic complexity, heterogeneity, and domain specificity of scientific data [9]. Scientific data sets can be represented in a variety of ways (tables, image, text, graphs, signals), often requiring extensive pre-processing, specialised evaluation metrics, and are subject to measurement noise, natural variability, and data imbalance [10].

A complete and statistically consistent uncertainty quantification for deep learning is provided, including the sources of uncertainty arising from (1) the new input data, (2) the training and testing data (3) the weight vectors of the neural network, and (4) the neural network because it is not a perfect predictor. Using Bayes Theorem and conditional probability densities, we demonstrate how each uncertainty source can be systematically quantified. We also introduce a fast and practical way to incorporate and combine all sources of errors for the first time. For illustration, the new method is applied to quantify errors in cloud autoconversion rates, predicted from an artificial neural network that was trained by aircraft cloud probe measurements in the Azores and the stochastic collection equation formulated as a two-moment bin model. For this specific example, the output uncertainty arising from uncertainty in the training and testing data is dominant, followed by uncertainty in the input data, in the trained neural network, and uncertainty in the weights. We discuss the usefulness of the methodology for machine learning practice, and how, through inclusion of uncertainty in the training data, the new methodology is less sensitive to input data that falls outside of the training data set.

Distribution shift is a common situation in machine learning tasks, where the data used for training a model is different from the data the model is applied to in the real world. This issue arises across multiple technical settings: from standard prediction tasks, to time-series forecasting, and to more recent applications of large language models (LLMs). This mismatch can lead to performance reductions, and can be related to a multiplicity of factors: sampling issues and non-representative data, changes in the environment or policies, or the emergence of previously unseen scenarios. This brief focuses on the definition and detection of distribution shifts in educational settings. We focus on standard prediction problems, where the task is to learn a model that takes in a series of input (predictors) $X=(x_1,x_2,...,x_m)$ and produces an output $Y=f(X)$.

In healthcare, detecting stress and enabling individuals to monitor their mental health and wellbeing is challenging. Advancements in wearable technology now enable continuous physiological data collection. This data can provide insights into mental health and behavioural states through psychophysiological analysis. However, automated analysis is required to provide timely results due to the quantity of data collected. Machine learning has shown efficacy in providing an automated classification of physiological data for health applications in controlled laboratory environments. Ambulatory uncontrolled environments, however, provide additional challenges requiring further modelling to overcome. This work empirically assesses several approaches utilising machine learning classifiers to detect stress using physiological data recorded in an ambulatory setting with self-reported stress annotations. A subset of the training portion SMILE dataset enables the evaluation of approaches before submission. The optimal stress detection approach achieves 90.77% classification accuracy, 91.24 F1-Score, 90.42 Sensitivity and 91.08 Specificity, utilising an ExtraTrees classifier and feature imputation methods. Meanwhile, accuracy on the challenge data is much lower at 59.23% (submission #54 from BEaTS-MTU, username ZacDair). The cause of the performance disparity is explored in this work.

The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment. In practice, the next-event prediction models are trained with sequential data collected at one time and need to generalize to newly arrived sequences in remote future, which requires models to handle temporal distribution shift from training to testing. In this paper, we first take a data-generating perspective to reveal a negative result that existing approaches with maximum likelihood estimation would fail for distribution shift due to the latent context confounder, i.e., the common cause for the historical events and the next event. Then we devise a new learning objective based on backdoor adjustment and further harness variational inference to make it tractable for sequence learning problems. On top of that, we propose a framework with hierarchical branching structures for learning context-specific representations. Comprehensive experiments on diverse tasks (e.g., sequential recommendation) demonstrate the effectiveness, applicability and scalability of our method with various off-the-shelf models as backbones.

The first part of this tutorial was about importing and cleaning the dataset. In this part, we will focus more on feature engineering, training, and evaluating the model. In the following part, we will run both the remove_repeating_subs() and build_training_sequences() functions. Note that for the sake of brevity, we won't include the code for both of these functions. The code for both functions can be found in the link below at the end of the tutorial.

There is increasing evidence of the business benefits of responsible AI (RAI), when companies mitigate risks through training and testing data, measuring model bias and accuracy, and model documentation. Companies that adopt responsible AI experience higher returns on their AI investment. Raj Shekhar writes that business leaders globally must coalesce around the imperative to develop rigorous, consistent standards for responsible AI adoption. Much has been spoken and written about the risks to public trust and safety arising from the adoption of artificial intelligence (AI)-based applications across multiple sectors. In finance, the use of AI has led to discriminatory credit decisions.

When building a predictive model, the quality of the results depends on the data you use. If you are using not enough or wrong data, your model will not be able to make realistic predictions and will lead you in the wrong direction. To avoid this, you need to understand the difference between training and testing data in machine learning. Without further ado, let's dive in. Let's say you want to create a model based on some database.