We propose a nested reduced-rank regression (NRRR) approach in fitting regression model with multivariate functional responses and predictors, to achieve tailored dimension reduction and facilitate interpretation/visualization of the resulting functional model. Our approach is based on a two-level low-rank structure imposed on the functional regression surfaces. A global low-rank structure identifies a small set of latent principal functional responses and predictors that drives the underlying regression association. A local low-rank structure then controls the complexity and smoothness of the association between the principal functional responses and predictors. Through a basis expansion approach, the functional problem boils down to an interesting integrated matrix approximation task, where the blocks or submatrices of an integrated low-rank matrix share some common row space and/or column space. An iterative algorithm with convergence guarantee is developed. We establish the consistency of NRRR and also show through non-asymptotic analysis that it can achieve at least a comparable error rate to that of the reduced-rank regression. Simulation studies demonstrate the effectiveness of NRRR. We apply NRRR in an electricity demand problem, to relate the trajectories of the daily electricity consumption with those of the daily temperatures.

Multi-way data analysis has become an essential tool for capturing underlying structures in higher-order data sets where standard two-way analysis techniques often fail to discover the hidden correlations between variables in multi-way data. We propose a multi-objective variational autoencoder (MVA) method for smart infrastructure damage detection and diagnosis in multi-way sensing data based on the reconstruction probability of autoencoder deep neural network (ADNN). Our method fuses data from multiple sensors in one ADNN at which informative features are being extracted and utilized for damage identification. It generates probabilistic anomaly scores to detect damage, asses its severity and further localize it via a new localization layer introduced in the ADNN. We evaluated our method on multi-way datasets in the area of structural health monitoring for damage diagnosis purposes. The data was collected from our deployed data acquisition system on a cable-stayed bridge in Western Sydney and from a laboratory based building structure obtained from Los Alamos National Laboratory (LANL). Experimental results show that the proposed method can accurately detect structural damage. It was also able to estimate the different levels of damage severity, and capture damage locations in an unsupervised aspect. Compared to the state-of-the-art approaches, our proposed method shows better performance in terms of damage detection and localization.

Legendre duality provides a variational lower-bound for the Kullback-Leibler divergence (KL) which can be estimated using samples, without explicit knowledge of the density ratio. We use this estimator, the \textit{KL Approximate Lower-bound Estimate} (KALE), in a contrastive setting for learning energy-based models, and show that it provides a maximum likelihood estimate (MLE). We then extend this procedure to adversarial training, where the discriminator represents the energy and the generator is the base measure of the energy-based model. Unlike in standard generative adversarial networks (GANs), the learned model makes use of both generator and discriminator to generate samples. This is achieved using Hamiltonian Monte Carlo in the latent space of the generator, using information from the discriminator, to find regions in that space that produce better quality samples. We also show that, unlike the KL, KALE enjoys smoothness properties that make it suitable for adversarial training, and provide convergence rates for KALE when the negative log density ratio belongs to the variational family. Finally, we demonstrate the effectiveness of this approach on simple datasets.

Channel attention mechanisms, as the key components of some modern convolutional neural networks (CNNs) architectures, have been commonly used in many visual tasks for effective performance improvement. It is able to reinforce the informative channels and to suppress useless channels of feature maps obtained by CNNs. Recently, different attention modules have been proposed, which are implemented in various ways. However, they are mainly based on convolution and pooling operations, which are lack of intuitive and reasonable insights about the principles that they are based on. Moreover, the ways that they improve the performance of the CNNs is not clear either. In this paper, we propose a Gaussian process embedded channel attention (GPCA) module and interpret the channel attention intuitively and reasonably in a probabilistic way. The GPCA module is able to model the correlations from channels which are assumed as beta distributed variables with Gaussian process prior. As the beta distribution is intractably integrated into the end-to-end training of the CNNs, we utilize an appropriate approximation of the beta distribution to make the distribution assumption implemented easily. In this case, the proposed GPCA module can be integrated into the end-to-end training of the CNNs. Experimental results demonstrate that the proposed GPCA module can improve the accuracies of image classification on four widely used datasets.

The US is a leader in investing capital into private AI with nearly US$12 billion. China, which came second with US$6.8 billion investment, also files more AI patents than any other country across the globe and three times more than Japan. The majority of AI patents filed between 2014-2018 were filed in the U.S. and Canada, and 94% of patents are filed in wealthy nations. Mergers and acquisitions worth $37 billion were spurred thanks to AI. At the same time, IPOs worth $34 billion were also associated with AI. Investment in AI startups recorded a rapid increase in the last ten years from a total of $1.3 billion raised in 2010 to over $40.4 billion.

Much has been written about the coronavirus since it was first identified in China in January and much more will undoubtedly be written before the subsequently alarming spread abates and medical science comes up with an effective cure. And while news of the steady increase in reported numbers of people infected by and dying from COVID-19, as it is now known, has been dire, the good news is that we are getting much better at predicting and tracking the spread of infectious diseases. Three out of four infectious diseases originate in other species but their rapid spread in humans is facilitated by our ever-increasing mobility. International travel is now such that a disease that might once have stayed relatively contained can now spread across the world in mere weeks. We saw this with the Severe Acute Respiratory Syndrome (SARS) virus in 2003 and we see it again today.

Much has been written about the coronavirus since it was first identified in China in January and much more will undoubtedly be written before the subsequently alarming spread abates and medical science comes up with an effective cure. And while news of the steady increase in reported numbers of people infected by and dying from COVID-19, as it is now known, has been dire, the good news is that we are getting much better at predicting and tracking the spread of infectious diseases. Three out of four infectious diseases originate in other species but their rapid spread in humans is facilitated by our ever-increasing mobility. International travel is now such that a disease that might once have stayed relatively contained can now spread across the world in mere weeks. We saw this with the Severe Acute Respiratory Syndrome (SARS) virus in 2003 and we see it again today.

"We're a world leading artificial intelligence (AI) platform that monitors real time and real-world events and provides all-round risk detection and solutions," Rod Moynihan told Insurance Business. Moynihan is the managing director of Dataminr in Australia and New Zealand, a global real-time information discovery company that is pioneering what it sees as ground-breaking technology for detecting, classifying, and determining the significance of public information in real time. Moynihan recently gave an interview to Insurance Business to explain how the platform works and how it can aid insurers. Using public information and data available from across the world, Dataminr's AI platform finds, dissects and quantifies a large amount of data to make sense of potentially large impact events that can affect customers. "It sorts through millions upon millions of publicly available data," explained Moynihan.

The online analysis of multi-way data stored in a tensor $\mathcal{X} \in \mathbb{R} ^{I_1 \times \dots \times I_N} $ has become an essential tool for capturing the underlying structures and extracting the sensitive features which can be used to learn a predictive model. However, data distributions often evolve with time and a current predictive model may not be sufficiently representative in the future. Therefore, incrementally updating the tensor-based features and model coefficients are required in such situations. A new efficient tensor-based feature extraction, named NeSGD, is proposed for online $CANDECOMP/PARAFAC$ (CP) decomposition. According to the new features obtained from the resultant matrices of NeSGD, a new criteria is triggered for the updated process of the online predictive model. Experimental evaluation in the field of structural health monitoring using laboratory-based and real-life structural datasets show that our methods provide more accurate results compared with existing online tensor analysis and model learning. The results showed that the proposed methods significantly improved the classification error rates, were able to assimilate the changes in the positive data distribution over time, and maintained a high predictive accuracy in all case studies.

Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult task. Problems could be the limited amount of data for impaired speech. Furthermore, acquiring more data and/or expertise is time-consuming and expensive. In this paper we position ourselves for the following speech processing tasks: Automatic Speech Recognition, speaker identification and emotion recognition. To assess the problem of limited data, we firstly investigate state-of-the-art Automatic Speech Recognition systems as it represents the hardest tasks (due to the large variability in each language). Next, we provide an overview of techniques and tasks requiring fewer data. In the last section we investigate few-shot techniques as we interpret under-resourced speech as a few-shot problem. In that sense we propose an overview of few-shot techniques and perspectives of using such techniques for the focused speech problems in this survey. It occurs that the reviewed techniques are not well adapted for large datasets. Nevertheless, some promising results from the literature encourage the usage of such techniques for speech processing.