Interpretation of deep learning remains a very challenging problem. Although the Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location, it fails to provide insight into the salient features used by the model to make decisions. Furthermore, existing evaluation protocols often overlook the correlation between interpretability performance and the model's decision quality, which presents a more fundamental issue. This paper proposes a new two-stage interpretability method called the Decomposition Class Activation Map (Decom-CAM), which offers a feature-level interpretation of the model's prediction. Decom-CAM decomposes intermediate activation maps into orthogonal features using singular value decomposition and generates saliency maps by integrating them. The orthogonality of features enables CAM to capture local features and can be used to pinpoint semantic components such as eyes, noses, and faces in the input image, making it more beneficial for deep model interpretation. To ensure a comprehensive comparison, we introduce a new evaluation protocol by dividing the dataset into subsets based on classification accuracy results and evaluating the interpretability performance on each subset separately. Our experiments demonstrate that the proposed Decom-CAM outperforms current state-of-the-art methods significantly by generating more precise saliency maps across all levels of classification accuracy. Combined with our feature-level interpretability approach, this paper could pave the way for a new direction for understanding the decision-making process of deep neural networks.

Despite recent advancements, NLP models continue to be vulnerable to bias. This bias often originates from the uneven distribution of real-world data and can propagate through the annotation process. Escalated integration of these models in our lives calls for methods to mitigate bias without overbearing annotation costs. While active learning (AL) has shown promise in training models with a small amount of annotated data, AL's reliance on the model's behavior for selective sampling can lead to an accumulation of unwanted bias rather than bias mitigation. However, infusing clustering with AL can overcome the bias issue of both AL and traditional annotation methods while exploiting AL's annotation efficiency. In this paper, we propose a novel adaptive clustering-based active learning algorithm, D-CALM, that dynamically adjusts clustering and annotation efforts in response to an estimated classifier error-rate. Experiments on eight datasets for a diverse set of text classification tasks, including emotion, hatespeech, dialog act, and book type detection, demonstrate that our proposed algorithm significantly outperforms baseline AL approaches with both pretrained transformers and traditional Support Vector Machines. D-CALM showcases robustness against different measures of information gain and, as evident from our analysis of label and error distribution, can significantly reduce unwanted model bias.

Fetal health is a critical concern during pregnancy as it can impact the well-being of both the mother and the baby. Regular monitoring and timely interventions are necessary to ensure the best possible outcomes. While there are various methods to monitor fetal health in the mother's womb, the use of artificial intelligence (AI) can improve the accuracy, efficiency, and speed of diagnosis. In this study, we propose a robust ensemble model called ensemble of tuned Support Vector Machine and ExtraTrees (ETSE) for predicting fetal health. Initially, we employed various data preprocessing techniques such as outlier rejection, missing value imputation, data standardization, and data sampling. Then, seven machine learning (ML) classifiers including Support Vector Machine (SVM), XGBoost (XGB), Light Gradient Boosting Machine (LGBM), Decision Tree (DT), Random Forest (RF), ExtraTrees (ET), and K-Neighbors were implemented. These models were evaluated and then optimized by hyperparameter tuning using the grid search technique. Finally, we analyzed the performance of our proposed ETSE model. The performance analysis of each model revealed that our proposed ETSE model outperformed the other models with 100% precision, 100% recall, 100% F1-score, and 99.66% accuracy. This indicates that the ETSE model can effectively predict fetal health, which can aid in timely interventions and improve outcomes for both the mother and the baby.

The robustness of a model for real-world deployment is decided by how well it performs on unseen data and distinguishes between in-domain and out-of-domain samples. Visual document classifiers have shown impressive performance on in-distribution test sets. However, they tend to have a hard time correctly classifying and differentiating out-of-distribution examples. Image-based classifiers lack the text component, whereas multi-modality transformer-based models face the token serialization problem in visual documents due to their diverse layouts. They also require a lot of computing power during inference, making them impractical for many real-world applications. We propose, GVdoc, a graph-based document classification model that addresses both of these challenges. Our approach generates a document graph based on its layout, and then trains a graph neural network to learn node and graph embeddings. Through experiments, we show that our model, even with fewer parameters, outperforms state-of-the-art models on out-of-distribution data while retaining comparable performance on the in-distribution test set.

NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in practice. In this paper, we propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift. These dimensions correspond to content word frequency divergences, syntactic divergences, and meaning changes not captured by word frequencies (e.g. lexical semantic change). We propose interpretable metrics for all three drift dimensions, and we modify past performance prediction methods to predict model performance at both the example and dataset level for English sentiment classification and natural language inference. We find that our drift metrics are more effective than previous metrics at predicting out-of-domain model accuracies (mean 16.8% root mean square error decrease), particularly when compared to popular fine-tuned embedding distances (mean 47.7% error decrease). Fine-tuned embedding distances are much more effective at ranking individual examples by expected performance, but decomposing into vocabulary, structural, and semantic drift produces the best example rankings of all considered model-agnostic drift metrics (mean 6.7% ROC AUC increase).

Ecological datasets are generally characterised by complex interactions between variables, nonlinearity, missing values, dependence in the observations and/or a continuously expanding size [1-3], especially since the recent increase in the use of remote sensing and automatic recorders [4]. A growing number of those datasets cannot be effectively processed by humans anymore and require methods that can deal with high number of variables and complex data structures [3, 5, 6]. Because of their ability to process large and complicated datasets, machine learning models are expected to become a standard framework in the analysis of ecological data [3, 7, 8]. Over the last few years, machine learning algorithms have become increasingly popular due to their high performance and flexibility [8]. In ecology, they have been successfully applied to perform various tasks such as identifying species from images or sounds [9], monitoring animal behaviour [10] or modelling species distribution [11] and new innovative studies and perspectives keep being regularly documented [3, 12]. However, implementing a machine learning model is not yet a trivial task and may seem intimidating to ecologists with no previous experience in this area. In this paper, we aim to share nine tips to help ecologists avoid some of the most common errors and incorrect practices in machine learning. We focused our tips on classification problems as a substantial number of ecological studies aim to assign data into predefined classes such as ecological states or biological entities. Some typical examples of classification include species identification through pictures [9] or sound recordings [13-15], distinction of different phenological phases in plant life cycle [16, 17], description of animal behaviour [18] and detection of disease in plants [19].

In the end-of-line test of geared motors, the evaluation of product qual-ity is important. Due to time constraints and the high diversity of variants, acous-tic measurements are more economical than vibration measurements. However, the acoustic data is affected by industrial disturbing noise. Therefore, the aim of this study is to investigate the robustness of features used for anomaly detection in geared motor end-of-line testing. A real-world dataset with typical faults and acoustic disturbances is recorded by an acoustic array. This includes industrial noise from the production and systematically produced disturbances, used to compare the robustness. Overall, it is proposed to apply features extracted from a log-envelope spectrum together with psychoacoustic features. The anomaly de-tection is done by using the isolation forest or the more universal bagging random miner. Most disturbances can be circumvented, while the use of a hammer or air pressure often causes problems. In general, these results are important for condi-tion monitoring tasks that are based on acoustic or vibration measurements. Fur-thermore, a real-world problem description is presented to improve common sig-nal processing and machine learning tasks.

Monitoring of prevalent airborne diseases such as COVID-19 characteristically involves respiratory assessments. While auscultation is a mainstream method for preliminary screening of disease symptoms, its utility is hampered by the need for dedicated hospital visits. Remote monitoring based on recordings of respiratory sounds on portable devices is a promising alternative, which can assist in early assessment of COVID-19 that primarily affects the lower respiratory tract. In this study, we introduce a novel deep learning approach to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds. The proposed approach leverages a novel hierarchical spectrogram transformer (HST) on spectrogram representations of respiratory sounds. HST embodies self-attention mechanisms over local windows in spectrograms, and window size is progressively grown over model stages to capture local to global context. HST is compared against state-of-the-art conventional and deep-learning baselines. Demonstrations on crowd-sourced multi-national datasets indicate that HST outperforms competing methods, achieving over 83% area under the receiver operating characteristic curve (AUC) in detecting COVID-19 cases.

Code generation from text requires understanding the user's intent from a natural language description and generating an executable code snippet that satisfies this intent. While recent pretrained language models demonstrate remarkable performance for this task, these models fail when the given natural language description is under-specified. In this work, we introduce a novel and more realistic setup for this task. We hypothesize that the under-specification of a natural language description can be resolved by asking clarification questions. Therefore, we collect and introduce a new dataset named CodeClarQA containing pairs of natural language descriptions and code with created synthetic clarification questions and answers. The empirical results of our evaluation of pretrained language model performance on code generation show that clarifications result in more precisely generated code, as shown by the substantial improvement of model performance in all evaluation metrics. Alongside this, our task and dataset introduce new challenges to the community, including when and what clarification questions should be asked. Our code and dataset are available on GitHub.

Adversarial attacks represent a security threat to machine learning based automatic speech recognition (ASR) systems. To prevent such attacks we propose an adversarial example detection strategy applicable to any ASR system that predicts a probability distribution over output tokens in each time step. We measure a set of characteristics of this distribution: the median, maximum, and minimum over the output probabilities, the entropy, and the Jensen-Shannon divergence of the distributions of subsequent time steps. Then, we fit a Gaussian distribution to the characteristics observed for benign data. By computing the likelihood of incoming new audio we can distinguish malicious inputs from samples from clean data with an area under the receiving operator characteristic (AUROC) higher than 0.99, which drops to 0.98 for less-quality audio. To assess the robustness of our method we build adaptive attacks. This reduces the AUROC to 0.96 but results in more noisy adversarial clips.