Contrastive self-supervised learning has recently benefited fMRI classification with inductive biases. Its weak label reliance prevents overfitting on small medical datasets and tackles the high intraclass variances. Nonetheless, existing contrastive methods generate resemblant pairs only on pixel-level features of 3D medical images, while the functional connectivity that reveals critical cognitive information is under-explored. Additionally, existing methods predict labels on individual contrastive representation without recognizing neighbouring information in the patient group, whereas interpatient contrast can act as a similarity measure suitable for population-based classification. We hereby proposed contrastive functional connectivity graph learning for population-based fMRI classification. Representations on the functional connectivity graphs are "repelled" for heterogeneous patient pairs meanwhile homogeneous pairs "attract" each other. Then a dynamic population graph that strengthens the connections between similar patients is updated for classification. Experiments on a multi-site dataset ADHD200 validate the superiority of the proposed method on various metrics. We initially visualize the population relationships and exploit potential subtypes.

There is a widespread belief that the tone of US political language has become more negative recently, in particular when Donald Trump entered politics. At the same time, there is disagreement as to whether Trump changed or merely continued previous trends. To date, data-driven evidence regarding these questions is scarce, partly due to the difficulty of obtaining a comprehensive, longitudinal record of politicians' utterances. Here we apply psycholinguistic tools to a novel, comprehensive corpus of 24 million quotes from online news attributed to 18,627 US politicians in order to analyze how the tone of US politicians' language evolved between 2008 and 2020. We show that, whereas the frequency of negative emotion words had decreased continuously during Obama's tenure, it suddenly and lastingly increased with the 2016 primary campaigns, by 1.6 pre-campaign standard deviations, or 8% of the pre-campaign mean, in a pattern that emerges across parties. The effect size drops by 40% when omitting Trump's quotes, and by 50% when averaging over speakers rather than quotes, implying that prominent speakers, and Trump in particular, have disproportionately, though not exclusively, contributed to the rise in negative language. This work provides the first large-scale data-driven evidence of a drastic shift toward a more negative political tone following Trump's campaign start as a catalyst, with important implications for the debate about the state of US politics.

This paper presents a simple method for speech videos generation based on audio: given a piece of audio, we can generate a video of the target face speaking this audio. We propose Generative Adversarial Networks (GAN) with cut speech audio input as condition and use Convolutional Gate Recurrent Unit (GRU) in generator and discriminator. Our model is trained by exploiting the short audio and the frames in this duration. For training, we cut the audio and extract the face in the corresponding frames. We designed a simple encoder and compare the generated frames using GAN with and without GRU. We use GRU for temporally coherent frames and the results show that short audio can produce relatively realistic output results.

Modeling biological soft tissue is complex in part due to material heterogeneity. Microstructural patterns, which play a major role in defining the mechanical behavior of these tissues, are both challenging to characterize, and difficult to simulate. Recently, machine learning-based methods to predict the mechanical behavior of heterogeneous materials have made it possible to more thoroughly explore the massive input parameter space associated with heterogeneous blocks of material. Specifically, we can train machine learning (ML) models to closely approximate computationally expensive heterogeneous material simulations where the ML model is trained on a dataset of simulations that capture the range of spatial heterogeneity present in the material of interest. However, when it comes to applying these techniques to biological tissue more broadly, there is a major limitation: the relevant microstructural patterns are both challenging to obtain and difficult to analyze. Consequently, the number of useful examples available to characterize the input domain under study is limited. In this work, we investigate the efficacy of ML-based generative models as well as procedural methods as a tool for augmenting limited input pattern datasets. We find that a Style-based Generative Adversarial Network with adaptive discriminator augmentation is able to successfully leverage just 1,000 example patterns to create the most authentic generated patterns. In general, diverse generated patterns with adequate resemblance to the real patterns can be used as inputs to finite element simulations to meaningfully augment the training dataset. To enable this methodological contribution, we have created an open access dataset of Finite Element Analysis simulations based on Cahn-Hilliard patterns. We anticipate that future researchers will be able to leverage this dataset and build on the work presented here.

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a unilateral dependency optimization strategy, i.e., minimizing the dependency between inputs (i.e., features) and outputs (i.e., labels) during training the classifier. However, such a minimization process conflicts with minimizing the supervised loss that aims to maximize the dependency between inputs and outputs, causing an explicit trade-off between model robustness against MI attacks and model utility on classification tasks. In this paper, we aim to minimize the dependency between the latent representations and the inputs while maximizing the dependency between latent representations and the outputs, named a bilateral dependency optimization (BiDO) strategy. In particular, we use the dependency constraints as a universally applicable regularizer in addition to commonly used losses for deep neural networks (e.g., cross-entropy), which can be instantiated with appropriate dependency criteria according to different tasks. To verify the efficacy of our strategy, we propose two implementations of BiDO, by using two different dependency measures: BiDO with constrained covariance (BiDO-COCO) and BiDO with Hilbert-Schmidt Independence Criterion (BiDO-HSIC). Experiments show that BiDO achieves the state-of-the-art defense performance for a variety of datasets, classifiers, and MI attacks while suffering a minor classification-accuracy drop compared to the well-trained classifier with no defense, which lights up a novel road to defend against MI attacks.

Submarines are valued primarily for his or her means to cover. The peace of mind that submarines would doubtless survive the primary missile strike in a nuclear struggle and thus be capable to reply by launching missiles in a second strike is essential to the technique of deterrence often called mutually assured destruction. Any new expertise which may render the oceans successfully clear, making it trivial to identify lurking submarines, might thus undermine the peace of the world. For almost a century, naval engineers have striven to develop ever-faster, ever-quieter submarines. However they've labored simply as laborious at advancing a wide selection of radar, sonar, and different applied sciences designed to detect, goal, and eradicate enemy submarines. The stability appeared to show with the emergence of nuclear-powered submarines within the early Sixties.

"The other thing is, because we're Allianz Partners, while it's mainly travel that we do in New Zealand, Allianz Partners globally is much more of an assistance company, so there's a whole lot of things that [the group does]." He continued: "What we did was we talked to our partners about some of the opportunities that we had and things that we could do with them, and areas where we thought we could help them to increase their reach-out to their customers." Essentially, it was a case of'What other things can we do while travel is limited,' and Allianz Partners NZ found its way towards the wellness realm, with the insurance company set to launch its digital health service (DHS) on July 18. "One of the things that [DHS] does for us is it provides our customers and business partners with immediate direct access to [five] key things," said Blyth. "Of those key things, one is an AI-based (artificial intelligence) symptom checker; the second is medical advice where they can chat with doctors." Other components of the health assistant include a round-the-clock healthline, a mental wellbeing feature, and a health services directory.

As the innovation paradigm in automotive industry shifted over time, artificial intelligence ("AI") has deeply penetrated into operation of automotive industry. Some manufacturers seek to utilize robots that learn automotive manufacturing skills, such as design, part manufacturing, and assembly, to assist human workers. AI are also utilized in aftermarket services, such as maintenance of engine or battery performance. Unsurprisingly, automotive industry faces new intellectual property challenges including those traditionally faced by AI technology patents. What if an AI develops a method of navigation or designs a new automotive?

During the last Australian election we ran an ambitious project that tracked campaign spending and political announcements by monitoring the Facebook pages of every major party politician and candidate. The project, dubbed the "pork-o-meter" (after the term pork-barreling), was hugely successful in being able to identify distinct patterns of spending based on vote margin, or incumbent party, with marginal electorates receiving billions of dollars more in campaign promises than other electorates. All up, we processed 34,061 Facebook posts, 2,452 media releases, and published eight stories (eg here, here and here) in addition to an interactive feature. We also used the same Facebook data to analyse photos posted during the campaign to break down the most common types of photo ops for each party, and how things have changed since the 2016 election. We were able to discover more than 1,600 election promises, amounting to tens of billions of dollars in potential spending.

Optimizing management practices and selecting the best cultivar for planting play a significant role in increasing agricultural food production and decreasing environmental footprint. In this study, we develop optimization frameworks under uncertainty using conditional value-at-risk in the stochastic programming objective function. We integrate the crop model, APSIM, and a parallel Bayesian optimization algorithm to optimize the management practices and select the best cultivar at different levels of risk aversion. This approach integrates the power of optimization in determining the best decisions and crop model in simulating nature's output corresponding to various decisions. As a case study, we set up the crop model for 25 locations across the US Corn Belt. We optimized the management options (planting date, N fertilizer amount, fertilizing date, and plant density in the farm) and cultivar options (cultivars with different maturity days) three times: a) before, b) at planting and c) after a growing season with known weather. Results indicated that the proposed model produced meaningful connections between weather and optima decisions. Also, we found risk-tolerance farmers get more expected yield than risk-averse ones in wet and non-wet weathers.