Cartoonists have captivated generations by humanising mice, from the enigmatic Mickey Mouse and charming Stuart Little to the smooth-talking Speedy Gonzales and wily Jerry, who continually outsmarts Tom, the dumb housecat. Turns out, they might have been onto something – at least when it comes to the little critters having emotions – according to research published in the journal Science. Back in 1872, Charles Darwin proposed that the universal, innate and communicative emotions of animals and humans can be best understood through facial expressions. Humans clearly use the same expressions to convey emotion. For instance, disgust makes us wrinkle our nose, narrow our eyes and distort our upper lip; if we're happy we smile and if something makes us sad our lips droop down at the edges.

A chest X-ray, analyzed by Qure.ai's software, picks up on abnormalities that suggest the likelihood of COVID-19 infection. X-rays are one of the quickest, simplest ways to diagnose the disease, and an army of AI specialists around the world are trying to speed up how the images are used to find cases. Most cite the lack of data as the prime obstacle to broader adoption of AI. For all the frantic effort to coordinate life-saving work around the globe during the COVID-19 pandemic, the digital age finds itself hampered in one very specific respect: information. Teams of artificial intelligence researchers are trying to bring decades of technology to bear on the problem of diagnosing and treating the disease, but the data they need to develop their software programs is scattered around the globe, making it practically inaccessible. The painful lack of data is evident in one particular use case for AI, the development of diagnostic tests for COVID-19 based on X-rays or on "computed tomography" scans of the lungs.

A future driven by artificial intelligence (AI) is often depicted as one paved with improvements across every aspect of life--from health, to jobs, to how we connect. But cracks in this utopia are starting to appear, particularly as we glimpse how AI can also be used to surveil, discriminate, and cause other harms. What existing legal frameworks can protect us from the dark side of this brave new world of technology? Facial recognition is a good example of an AI-driven technology that is starting to have a dramatic human impact. When facial recognition is used to unlock a smartphone, the risk of harm is low, but the stakes are much higher when it is used for policing.

Contextual multi-armed bandit (MAB) achieves cutting-edge performance on a variety of problems. When it comes to real-world scenarios such as recommendation system and online advertising, however, it is essential to consider the resource consumption of exploration. In practice, there is typically non-zero cost associated with executing a recommendation (arm) in the environment, and hence, the policy should be learned with a fixed exploration cost constraint. It is challenging to learn a global optimal policy directly, since it is a NP-hard problem and significantly complicates the exploration and exploitation trade-off of bandit algorithms. Existing approaches focus on solving the problems by adopting the greedy policy which estimates the expected rewards and costs and uses a greedy selection based on each arm's expected reward/cost ratio using historical observation until the exploration resource is exhausted. However, existing methods are hard to extend to infinite time horizon, since the learning process will be terminated when there is no more resource. In this paper, we propose a hierarchical adaptive contextual bandit method (HATCH) to conduct the policy learning of contextual bandits with a budget constraint. HATCH adopts an adaptive method to allocate the exploration resource based on the remaining resource/time and the estimation of reward distribution among different user contexts. In addition, we utilize full of contextual feature information to find the best personalized recommendation. Finally, in order to prove the theoretical guarantee, we present a regret bound analysis and prove that HATCH achieves a regret bound as low as $O(\sqrt{T})$. The experimental results demonstrate the effectiveness and efficiency of the proposed method on both synthetic data sets and the real-world applications.

Training in supervised deep learning is computationally demanding, and the convergence behavior is usually not fully understood. We introduce and study a second-order stochastic quasi-Gauss--Newton (SQGN) optimization method that combines ideas from stochastic quasi-Newton methods, Gauss--Newton methods, and variance reduction to address this problem. SQGN provides excellent accuracy without the need for experimenting with many hyper-parameter configurations, which is often computationally prohibitive given the number of combinations and the cost of each training process. We discuss the implementation of SQGN with TensorFlow, and we compare its convergence and computational performance to selected first-order methods using the MNIST benchmark and a large-scale seismic tomography application from Earth science.

The Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM) has been used widely as a natural Bayesian nonparametric extension of the classical Hidden Markov Model for learning from sequential and time-series data. A sticky extension of the HDP-HMM has been proposed to strengthen the self-persistence probability in the HDP-HMM. However, the sticky HDP-HMM entangles the strength of the self-persistence prior and transition prior together, limiting its expressiveness. Here, we propose a more general model: the disentangled sticky HDP-HMM (DS-HDP-HMM). We develop novel Gibbs sampling algorithms for efficient inference in this model. We show that the disentangled sticky HDP-HMM outperforms the sticky HDP-HMM and HDP-HMM on both synthetic and real data, and apply the new approach to analyze neural data and segment behavioral video data.

With the rapid emergence of deep learning (DL) technology, it has been successfully used in various fields including aquaculture. This change can create new opportunities and a series of challenges for information and data processing in smart fish farming. This paper focuses on the applications of DL in aquaculture, including live fish identification, species classification, behavioral analysis, feeding decision-making, size or biomass estimation, water quality prediction. In addition, the technical details of DL methods applied to smart fish farming are also analyzed, including data, algorithms, computing power, and performance. The results of this review show that the most significant contribution of DL is the ability to automatically extract features. However, challenges still exist; DL is still in an era of weak artificial intelligence. A large number of labeled data are needed for training, which has become a bottleneck restricting further DL applications in aquaculture. Nevertheless, DL still offers breakthroughs in the handling of complex data in aquaculture. In brief, our purpose is to provide researchers and practitioners with a better understanding of the current state of the art of DL in aquaculture, which can provide strong support for the implementation of smart fish farming.

Fast testing can help mitigate the coronavirus disease 2019 (COVID-19) pandemic. Despite their accuracy for single sample analysis, infectious diseases diagnostic tools, like RT-PCR, require substantial resources to test large populations. We develop a scalable approach for determining the viral status of pooled patient samples. Our approach converts group testing to a linear inverse problem, where false positives and negatives are interpreted as generated by a noisy communication channel, and a message passing algorithm estimates the illness status of patients. Numerical results reveal that our approach estimates patient illness using fewer pooled measurements than existing noisy group testing algorithms. Our approach can easily be extended to various applications, including where false negatives must be minimized. Finally, in a Utopian world we would have collaborated with RT-PCR experts; it is difficult to form such connections during a pandemic. We welcome new collaborators to reach out and help improve this work!

Distributions are fundamental statistical elements that play essential theoretical and practical roles. The article discusses experiences of training neural networks to classify univariate empirical distributions and to represent them on the two-dimensional latent space forcing disentanglement based on the inputs of cumulative distribution functions (CDF). The latent space representation has been performed using an unsupervised beta variational autoencoder (beta-VAE). It separates distributions of different shapes while overlapping similar ones and empirically realises relationships between distributions that are known theoretically. The synthetic experiment of generated univariate continuous and discrete (Bernoulli) distributions with varying sample sizes and parameters has been performed to support the study. The representation on the latent two-dimensional coordinate system can be seen as an additional metadata of the real-world data that disentangles important distribution characteristics, such as shape of the CDF, classification probabilities of underlying theoretical distributions and their parameters, information entropy, and skewness. Entropy changes, providing an "arrow of time", determine dynamic trajectories along representations of distributions on the latent space. In addition, post beta-VAE unsupervised segmentation of the latent space based on weight-of-evidence (WOE) of posterior versus standard isotopic two-dimensional normal densities has been applied detecting the presence of assignable causes that distinguish exceptional CDF inputs.

Deep neural networks are revolutionizing the way complex systems are developed. However, these automatically-generated networks are opaque to humans, making it difficult to reason about them and guarantee their correctness. Here, we propose a novel approach for verifying properties of a widespread variant of neural networks, called recurrent neural networks. Recurrent neural networks play a key role in, e.g., natural language processing, and their verification is crucial for guaranteeing the reliability of many critical systems. Our approach is based on the inference of invariants, which allow us to reduce the complex problem of verifying recurrent networks into simpler, non-recurrent problems. Experiments with a proof-of-concept implementation of our approach demonstrate that it performs orders-of-magnitude better than the state of the art.