Training deep learning models with limited labelled data is an attractive scenario for many NLP tasks, including document classification. While with the recent emergence of BERT, deep learning language models can achieve reasonably good performance in document classification with few labelled instances, there is a lack of evidence in the utility of applying BERT-like models on long document classification. This work introduces a long-text-specific model -- the Hierarchical BERT Model (HBM) -- that learns sentence-level features of the text and works well in scenarios with limited labelled data. Various evaluation experiments have demonstrated that HBM can achieve higher performance in document classification than the previous state-of-the-art methods with only 50 to 200 labelled instances, especially when documents are long. Also, as an extra benefit of HBM, the salient sentences identified by learned HBM are useful as explanations for labelling documents based on a user study.
Anomaly detection is a challenging problem in machine learning, and is even more so when dealing with instances that are captured in low-level, raw data representations without a well-behaved set of engineered features. The Radial Basis Function Data Descriptor (RBFDD) network is an effective solution for anomaly detection, however, it is a shallow model that does not deal effectively with raw data representations. This paper investigates approaches to modifying the RBFDD network to transform it into a deep one-class classifier suitable for anomaly detection problems with low-level raw data representations. We show that approaches based on transfer learning are not effective and our results suggest that this is because the latent representations learned by generic classification models are not suitable for anomaly detection. Instead we show that an approach that adds multiple convolutional layers before the RBF layer, to form a Deep Radial Basis Function Data Descriptor (D-RBFDD) network, is very effective. This is shown in a set of evaluation experiments using multiple anomaly detection scenarios created from publicly available image classification datasets, and a real-world anomaly detection dataset in which different types of arrhythmia are detected in electrocardiogram (ECG) data. Our experiments show that the D-RBFDD network out-performs state-of-the-art anomaly detection methods including the Deep Support Vector Data Descriptor (Deep SVDD), One-Class SVM, and Isolation Forest on the image datasets, and produces competitive results for the ECG dataset.
The dairy industry uses clover and grass as fodder for cows. Accurate estimation of grass and clover biomass yield enables smart decisions in optimizing fertilization and seeding density, resulting in increased productivity and positive environmental impact. Grass and clover are usually planted together, since clover is a nitrogen-fixing plant that brings nutrients to the soil. Adjusting the right percentages of clover and grass in a field reduces the need for external fertilization. Existing approaches for estimating the grass-clover composition of a field are expensive and time consuming - random samples of the pasture are clipped and then the components are physically separated to weigh and calculate percentages of dry grass, clover and weeds in each sample. There is growing interest in developing novel deep learning based approaches to non-destructively extract pasture phenotype indicators and biomass yield predictions of different plant species from agricultural imagery collected from the field. Providing these indicators and predictions from images alone remains a significant challenge. Heavy occlusions in the dense mixture of grass, clover and weeds make it difficult to estimate each component accurately. Moreover, although supervised deep learning models perform well with large datasets, it is tedious to acquire large and diverse collections of field images with precise ground truth for different biomass yields. In this paper, we demonstrate that applying data augmentation and transfer learning is effective in predicting multi-target biomass percentages of different plant species, even with a small training dataset. The scheme proposed in this paper used a training set of only 261 images and provided predictions of biomass percentages of grass, clover, white clover, red clover, and weeds with mean absolute error of 6.77%, 6.92%, 6.21%, 6.89%, and 4.80% respectively.
Mastitis is a billion dollar health problem for the modern dairy industry, with implications for antibiotic resistance. The use of AI techniques to identify the early onset of this disease, thus has significant implications for the sustainability of this agricultural sector. Current approaches to treating mastitis involve antibiotics and this practice is coming under ever increasing scrutiny. Using machine learning models to identify cows at risk of developing mastitis and applying targeted treatment regimes to only those animals promotes a more sustainable approach. Incorrect predictions from such models, however, can lead to monetary losses, unnecessary use of antibiotics, and even the premature death of animals, so it is important to generate compelling explanations for predictions to build trust with users and to better support their decision making. In this paper we demonstrate a system developed to predict mastitis infections in cows and provide explanations of these predictions using counterfactuals. We demonstrate the system and describe the engagement with farmers undertaken to build it.
The aim of this study was to build a modelling framework that would allow us to be able to detect mastitis infections before they would normally be found by farmers through the introduction of machine learning techniques. In the making of this we created two different modelling framework's, one that works on the premise of detecting Sub Clinical mastitis infections at one Somatic Cell Count recording in advance called SMA and the other tries to detect both Sub Clinical mastitis infections aswell as Clinical mastitis infections at any time the cow is milked called AMA. We also introduce the idea of two different feature sets for our study, these represent different characteristics that should be taken into account when detecting infections, these were the idea of a cow differing to a farm mean and also trends in the lactation. We reported that the results for SMA are better than those created by AMA for Sub Clinical infections yet it has the significant disadvantage of only being able to classify Sub Clinical infections due to how we recorded Sub Clinical infections as being any time a Somatic Cell Count measurement went above a certain threshold where as CM could appear at any stage of lactation. Thus in some cases the lower accuracy values for AMA might in fact be more beneficial to farmers.
Deep neural networks have been successful in diverse discriminative classification tasks, although, they are poorly calibrated often assigning high probability to misclassified predictions. Potential consequences could lead to trustworthiness and accountability of the models when deployed in real applications, where predictions are evaluated based on their confidence scores. Existing solutions suggest the benefits attained by combining deep neural networks and Bayesian inference to quantify uncertainty over the models' predictions for ambiguous datapoints. In this work we propose to validate and test the efficacy of likelihood based models in the task of out of distribution detection (OoD). Across different datasets and metrics we show that Bayesian deep learning models on certain occasions marginally outperform conventional neural networks and in the event of minimal overlap between in/out distribution classes, even the best models exhibit a reduction in AUC scores in detecting OoD data. Preliminary investigations indicate the potential inherent role of bias due to choices of initialisation, architecture or activation functions. We hypothesise that the sensitivity of neural networks to unseen inputs could be a multi-factor phenomenon arising from the different architectural design choices often amplified by the curse of dimensionality. Furthermore, we perform a study to find the effect of the adversarial noise resistance methods on in and out-of-distribution performance, as well as, also investigate adversarial noise robustness of Bayesian deep learners.
A common assumption of novelty detection is that the distribution of both "normal" and "novel" data are static. However, this is often not the case in scenarios where data evolves over time, or when the definition of normal and novel depends on contextual information, leading to changes in these distributions. This can lead to significant difficulties when attempting to train a model on datasets where the distribution of normal data in one scenario is similar to that of novel data in another scenario. In this paper we propose a context-aware approach to novelty detection for deep autoencoders. We create a semi-supervised network architecture which utilises auxiliary labels in order to reveal contextual information and allows the model to adapt to a variety of normal and novel scenarios. We evaluate our approach on both synthetic image data and real world audio data displaying these characteristics.
Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations---particularly from their lack of robustness and over-sensitivity to out of distribution samples. Bayesian Neural Networks, due to their formulation under the Bayesian framework, provide a principled approach to building neural networks that address these limitations. This paper describes a study that empirically evaluates and compares Bayesian Neural Networks to their equivalent point estimate Deep Neural Networks to quantify the predictive uncertainty induced by their parameters, as well as their performance in view of this uncertainty. In this study, we evaluated and compared three point estimate deep neural networks against comparable Bayesian neural network alternatives using two well-known benchmark image classification datasets (CIFAR-10 and SVHN).