This work is motivated by an application in an industrial context, where the activity of sensors is recorded at a high frequency. The objective is to automatically detect abnormal measurement behaviour. Considering the sensor measures as functional data, we are formally interested in detecting outliers in a multivariate functional data set. Due to the heterogeneity of this data set, the proposed contaminated mixture model both clusters the multivariate functional data into homogeneous groups and detects outliers. The main advantage of this procedure over its competitors is that it does not require us to specify the proportion of outliers. Model inference is performed through an Expectation-Conditional Maximization algorithm, and the BIC criterion is used to select the number of clusters. Numerical experiments on simulated data demonstrate the high performance achieved by the inference algorithm. In particular, the proposed model outperforms competitors. Its application on the real data which motivated this study allows us to correctly detect abnormal behaviours.

NLP has achieved great progress in the past decade through the use of neural models and large labeled datasets. The dependence on abundant data prevents NLP models from being applied to low-resource settings or novel tasks where significant time, money, or expertise is required to label massive amounts of textual data. Recently, data augmentation methods have been explored as a means of improving data efficiency in NLP. To date, there has been no systematic empirical overview of data augmentation for NLP in the limited labeled data setting, making it difficult to understand which methods work in which settings. In this paper, we provide an empirical survey of recent progress on data augmentation for NLP in the limited labeled data setting, summarizing the landscape of methods (including token-level augmentations, sentence-level augmentations, adversarial augmentations, and hidden-space augmentations) and carrying out experiments on 11 datasets covering topics/news classification, inference tasks, paraphrasing tasks, and single-sentence tasks. Based on the results, we draw several conclusions to help practitioners choose appropriate augmentations in different settings and discuss the current challenges and future directions for limited data learning in NLP.

The main challenge for domain generalization (DG) is to overcome the potential distributional shift between multiple training domains and unseen test domains. One popular class of DG algorithms aims to learn representations that have an invariant causal relation across the training domains. However, certain features, called \emph{pseudo-invariant features}, may be invariant in the training domain but not the test domain and can substantially decreases the performance of existing algorithms. To address this issue, we propose a novel algorithm, called Invariant Information Bottleneck (IIB), that learns a minimally sufficient representation that is invariant across training and testing domains. By minimizing the mutual information between the representation and inputs, IIB alleviates its reliance on pseudo-invariant features, which is desirable for DG. To verify the effectiveness of the IIB principle, we conduct extensive experiments on large-scale DG benchmarks. The results show that IIB outperforms invariant learning baseline (e.g. IRM) by an average of 2.8\% and 3.8\% accuracy over two evaluation metrics.

Are you overwhelmed by the vast array of X-formers? X-formers are the name being given to the wide array of Transformer variants that have been implemented or proposed. You likely know Transformers from their recent spate of success stories in natural language processing, computer vision, and other areas of artificial intelligence, but are familiar with all of the X-formers? More importantly, do you know the differences, and why you might use one over another? A Survey of Transformers, by Tianyang Lin, Yuxin Wang, Xiangyang Liu, and Xipeng Qiu, has been written to help interested readers in this regard.

Network Traffic Classification (NTC) has become an important component in a wide variety of network management operations, e.g., Quality of Service (QoS) provisioning and security purposes. Machine Learning (ML) algorithms as a common approach for NTC methods can achieve reasonable accuracy and handle encrypted traffic. However, ML-based NTC techniques suffer from the shortage of labeled traffic data which is the case in many real-world applications. This study investigates the applicability of an active form of ML, called Active Learning (AL), which reduces the need for a high number of labeled examples by actively choosing the instances that should be labeled. The study first provides an overview of NTC and its fundamental challenges along with surveying the literature in the field of using ML techniques in NTC. Then, it introduces the concepts of AL, discusses it in the context of NTC, and review the literature in this field. Further, challenges and open issues in the use of AL for NTC are discussed. Additionally, as a technical survey, some experiments are conducted to show the broad applicability of AL in NTC. The simulation results show that AL can achieve high accuracy with a small amount of data.

This course will give an overview of all the topics we shall be looking at in this course. We shall begin by describing the oil value chain – the exploration and development, how oil is produced, shipped, and marketed. Moving further, we will learn about the importance of oil in the industry, both as a fuel and as a raw material in various forms in the global economy. Then, we will go through a brief history of oil – how it all began, and the different'kinds' of oil discoverers. We will be introduced to the major players in the oil market – the top producers and the major consumers. We will then see how oil is formed, how it sits deep within the earth and how we discover and refine it. We will learn about the different types of oils, and the methods employed to extract them. This will be followed by a brief overview of the different means of transporting oil, and the risks and benefits associated with the different methods of oil transport. Lastly, we shall look into the different oil benchmarks that prevail globally.

Despite the high accuracy offered by state-of-the-art deep natural-language models (e.g. LSTM, BERT), their application in real-life settings is still widely limited, as they behave like a black-box to the end-user. Hence, explainability is rapidly becoming a fundamental requirement of future-generation data-driven systems based on deep-learning approaches. Several attempts to fulfill the existing gap between accuracy and interpretability have been done. However, robust and specialized xAI (Explainable Artificial Intelligence) solutions tailored to deep natural-language models are still missing. We propose a new framework, named T-EBAnO, which provides innovative prediction-local and class-based model-global explanation strategies tailored to black-box deep natural-language models. Given a deep NLP model and the textual input data, T-EBAnO provides an objective, human-readable, domain-specific assessment of the reasons behind the automatic decision-making process. Specifically, the framework extracts sets of interpretable features mining the inner knowledge of the model. Then, it quantifies the influence of each feature during the prediction process by exploiting the novel normalized Perturbation Influence Relation index at the local level and the novel Global Absolute Influence and Global Relative Influence indexes at the global level. The effectiveness and the quality of the local and global explanations obtained with T-EBAnO are proved on (i) a sentiment analysis task performed by a fine-tuned BERT model, and (ii) a toxic comment classification task performed by an LSTM model.

The philosopher Mark Coeckelbergh has long been dealing with the development of intelligent machines and their effects on concepts of humanity, societal transformation and the ideology of the trans- and posthuman. His recent book AI Ethics (MIT Press, 2020) provides a survey of the most pressing moral questions opened up by these developments. Should we simply enjoy the new liberties generated by AI as future offers without any alternative? Where does selflessness end with respect to the machinic "other," and where should deliberations about a "trustworthy" AI start? Questions like these are tackled by Coeckelbergh in the following interview.

The advancements in neural networks and the on-demand need for accurate and near real-time Speech Emotion Recognition (SER) in human–computer interactions make it mandatory to compare available methods and databases in SER to achieve feasible solutions and a firmer understanding of this open-ended problem. The current study reviews deep learning approaches for SER with available datasets, followed by conventional machine learning techniques for speech emotion recognition. Ultimately, we present a multi-aspect comparison between practical neural network approaches in speech emotion recognition. The goal of this study is to provide a survey of the field of discrete speech emotion recognition.

The company will also hold the Avnet 2021 Artificial Intelligence Cloud Conference on 29 June, 2021. Joined by developers, engineers, and decision makers in the AI field, the summit will feature cutting-edge technology trends in artificial intelligence and machine learning, and in-depth discussions on the development, future prospects and blueprints for AI to encourage and accelerate innovation. "MarketsandMarkets forecasts the global artificial intelligence market size to grow to over USD$300 billion by 2026, and the market in Asia Pacific is anticipated to grow at the highest CAGR during the forecast period," says KS Lim, senior director of supplier management at Avnet Asia. "As the world's leading technology distributor and solution provider, Avnet has a comprehensive ecosystem that provides customers with end-to-end artificial intelligence and machine learning solutions, reducing the cost and complexity of product development to enable application scenarios," he says. "We will continue to work hand in hand with our suppliers and partners to further contribute to the development and maturity of the entire AI ecosystem."