Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used during training and the model-generated prefixes used at inference time. Scheduled sampling is a simple and empirically successful approach which addresses this issue by incorporating model-generated prefixes into training. However, it has been argued that it is an inconsistent training objective leading to models ignoring the prefixes altogether. In this paper, we conduct systematic experiments and find that scheduled sampling, while it ameliorates exposure bias by increasing model reliance on the input sequence, worsens performance when the prefix at inference time is correct, a form of catastrophic forgetting. We propose to use Elastic Weight Consolidation to better balance mitigating exposure bias with retaining performance. Experiments on four IWSLT'14 and WMT'14 translation datasets demonstrate that our approach alleviates catastrophic forgetting and significantly outperforms maximum likelihood estimation and scheduled sampling baselines.

The increasingly wide usage of location aware sensors has made it possible to collect large volume of trajectory data in diverse application domains. Machine learning allows to study the activities or behaviours of moving objects (e.g., people, vehicles, robot) using such trajectory data with rich spatiotemporal information to facilitate informed strategic and operational decision making. In this study, we consider the task of classifying the activities of moving objects from their noisy indoor trajectory data in a collaborative manufacturing environment. Activity recognition can help manufacturing companies to develop appropriate management policies, and optimise safety, productivity, and efficiency. We present a semi-supervised machine learning approach that first applies an information theoretic criterion to partition a long trajectory into a set of segments such that the object exhibits homogeneous behaviour within each segment. The segments are then labelled automatically based on a constrained hierarchical clustering method. Finally, a deep learning classification model based on convolutional neural networks is trained on trajectory segments and the generated pseudo labels. The proposed approach has been evaluated on a dataset containing indoor trajectories of multiple workers collected from a tricycle assembly workshop. The proposed approach is shown to achieve high classification accuracy (F-score varies between 0.81 to 0.95 for different trajectories) using only a small proportion of labelled trajectory segments.

This dataset encompasses fluorescence spectra and chemical parameters of 24 olive oil samples from the 2019-2020 harvest provided by the producer Conde de Benalua, Granada, Spain. The oils are characterized by different qualities: 10 extra virgin olive oil (EVOO), 8 virgin olive oil (VOO), and 6 lampante olive oil (LOO) samples. For each sample, the dataset includes fluorescence spectra obtained with two excitation wavelengths, oil quality, and five chemical parameters necessary for the quality assessment of olive oil. The fluorescence spectra were obtained by exciting the samples at 365 nm and 395 nm under identical conditions. The dataset includes the values of the following chemical parameters for each olive oil sample: acidity, peroxide value, K270, K232, ethyl esters, and the quality of the samples (EVOO, VOO, or LOO). The dataset offers a unique possibility for researchers in food technology to develop machine learning models based on fluorescence data for the quality assessment of olive oil due to the availability of both spectroscopic and chemical data. The dataset can be used, for example, to predict one or multiple chemical parameters or to classify samples based on their quality from fluorescence spectra.

Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations. DMIL adopts a novel cooperative-yet-adversarial learning strategy, which uses the discriminator to guide and couple the learning process of the policy and dynamics model, resulting in improved model performance and robustness. Our framework can also be extended to the case when demonstrations contain a large proportion of suboptimal data. Experimental results show that DMIL and its extension achieve superior performance and robustness compared to state-of-the-art offline IL methods under small datasets.

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In contrast to the plain-text modeling as the focus of the PrLMs, dialogue texts involve multiple speakers and reflect special characteristics such as topic transitions and structure dependencies between distant utterances. However, the related PrLM models commonly represent dialogues sequentially by processing the pairwise dialogue history as a whole. Thus the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose compositional learning for holistic interaction across the utterances beyond the sequential contextualization from PrLMs, in order to capture the utterance-aware and speaker-aware representations entailed in a dialogue history. We decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, and two speaker roles (i.e., utterances of sender and utterances of the receiver), respectively. In addition, we employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets, achieving new state-of-the-art performance over previous methods.

Supervised approaches generally rely on majority-based labels. However, it is hard to achieve high agreement among annotators in subjective tasks such as hate speech detection. Existing neural network models principally regard labels as categorical variables, while ignoring the semantic information in diverse label texts. In this paper, we propose AnnoBERT, a first-of-its-kind architecture integrating annotator characteristics and label text with a transformer-based model to detect hate speech, with unique representations based on each annotator's characteristics via Collaborative Topic Regression (CTR) and integrate label text to enrich textual representations. During training, the model associates annotators with their label choices given a piece of text; during evaluation, when label information is not available, the model predicts the aggregated label given by the participating annotators by utilising the learnt association. The proposed approach displayed an advantage in detecting hate speech, especially in the minority class and edge cases with annotator disagreement. Improvement in the overall performance is the largest when the dataset is more label-imbalanced, suggesting its practical value in identifying real-world hate speech, as the volume of hate speech in-the-wild is extremely small on social media, when compared with normal (non-hate) speech. Through ablation studies, we show the relative contributions of annotator embeddings and label text to the model performance, and tested a range of alternative annotator embeddings and label text combinations.

We present FOLD-SE, an efficient, explainable machine learning algorithm for classification tasks given tabular data containing numerical and categorical values. FOLD-SE generates a set of default rules-essentially a stratified normal logic program-as an (explainable) trained model. Explainability provided by FOLD-SE is scalable, meaning that regardless of the size of the dataset, the number of learned rules and learned literals stay quite small while good accuracy in classification is maintained. A model with smaller number of rules and literals is easier to understand for human beings. FOLD-SE is competitive with state-of-the-art machine learning algorithms such as XGBoost and Multi-Layer Perceptrons (MLP) wrt accuracy of prediction. However, unlike XGBoost and MLP, the FOLD-SE algorithm is explainable. The FOLD-SE algorithm builds upon our earlier work on developing the explainable FOLD-R++ machine learning algorithm for binary classification and inherits all of its positive features. Thus, pre-processing of the dataset, using techniques such as one-hot encoding, is not needed. Like FOLD-R++, FOLD-SE uses prefix sum to speed up computations resulting in FOLD-SE being an order of magnitude faster than XGBoost and MLP in execution speed. The FOLD-SE algorithm outperforms FOLD-R++ as well as other rule-learning algorithms such as RIPPER in efficiency, performance and scalability, especially for large datasets. A major reason for scalable explainability of FOLD-SE is the use of a literal selection heuristics based on Gini Impurity, as opposed to Information Gain used in FOLD-R++. A multi-category classification version of FOLD-SE is also presented.

Researchers in Switzerland and Australia have used machine learning to crack the code governing charge transfer and colour emission in chains of molecules. Chains of molecules, known as polymers, can be put together in patterns to create different visual effects, such as emitting a certain colour when exposed to ultraviolet light or other light sources. Polymers are used in data storage, security inks, organic light-emitting diodes (OLEDs), and even the solar energy industry. Until now, getting the molecules in the right order to create the desired effect has been a slow process of trial and error, limiting its practical application and usefulness. To solve this problem, Exciton Science Research Fellow Dr Nastaran Meftahi of RMIT University, under the supervision of Professor Salvy Russo, trained a machine learning model to better understand the behaviour occurring inside and between the molecules.

You might be rolling your eyes as you see the drone take off to the skies and hover over the Australian coastline, camera angled straight down towards the glistening turquoise water. "Another TikTok influencer trying to get the perfect shot," you grumble to yourself. But if you look closely at the pilot, you'll notice they've got a sign next to them that says "Keep Clear" in bright yellow and red letters. Drones have been a helpful tool in spotted sharks from the skies. It's an Australian surf lifesaver, using the above drone to spot sharks at the beach before they get too close to swimmers like yourself.

Understanding the ambient scene is imperative for several applications such as autonomous driving and navigation. While obtaining real-world image data with per-pixel labels is challenging, existing accurate synthetic image datasets primarily focus on indoor spaces with fixed lighting and scene participants, thereby severely limiting their application to outdoor scenarios. In this work we introduce OmniHorizon, a synthetic dataset with 24,335 omnidirectional views comprising of a broad range of indoor and outdoor spaces consisting of buildings, streets, and diverse vegetation. Our dataset also accounts for dynamic scene components including lighting, different times of a day settings, pedestrians, and vehicles. Furthermore, we also demonstrate a learned synthetic-to-real cross-domain inference method for in-the-wild 3D scene depth and normal estimation method using our dataset. To this end, we propose UBotNet, an architecture based on a UNet and a Bottleneck Transformer, to estimate scene-consistent normals. We show that UBotNet achieves significantly improved depth accuracy (4.6%) and normal estimation (5.75%) compared to several existing networks such as U-Net with skip-connections. Finally, we demonstrate in-the-wild depth and normal estimation on real-world images with UBotNet trained purely on our OmniHorizon dataset, showing the promise of proposed dataset and network for scene understanding.