Time series forecasting based on deep architectures has been gaining popularity in recent years due to their ability to model complex non-linear temporal dynamics. The recurrent neural network is one such model capable of handling variable-length input and output. In this paper, we leverage recent advances in deep generative models and the concept of state space models to propose a stochastic adaptation of the recurrent neural network for multistep-ahead time series forecasting, which is trained with stochastic gradient variational Bayes. In our model design, the transition function of the recurrent neural network, which determines the evolution of the hidden states, is stochastic rather than deterministic as in a regular recurrent neural network; this is achieved by incorporating a latent random variable into the transition process which captures the stochasticity of the temporal dynamics. Our model preserves the architectural workings of a recurrent neural network for which all relevant information is encapsulated in its hidden states, and this flexibility allows our model to be easily integrated into any deep architecture for sequential modelling. We test our model on a wide range of datasets from finance to healthcare; results show that the stochastic recurrent neural network consistently outperforms its deterministic counterpart.

A written proposal to ban several uses of artificial intelligence (AI) and to place new oversight on other "high-risk" AI applications--published by the European Commission this week--met fierce opposition from several digital rights advocates in Europe. Portrayed as a missed opportunity by privacy experts, the EU Commission's proposal bans four broad applications of AI, but it includes several loopholes that could lead to abuse, and it fails to include a mechanism to add other AI applications to the ban list. It deems certain types of AI applications as "high-risk"--meaning their developers will need to abide by certain restrictions--but some of those same applications were specifically called out by many digital rights groups earlier this year as "incompatible with a democratic society." It creates new government authorities, but the responsibilities of those authorities may overlap with separate authorities devoted to overall data protection. Most upsetting to digital rights experts, it appears, is that the 107-page document (not including the necessary annexes) offers only glancing restrictions on biometric surveillance, like facial recognition software.

My friend Robert Burton, a neurologist and author, wanted to share a song with me last year, and sent me a link to an NPR Tiny Desk Concert. "It's wonderful to see truly new and inspiring music," he wrote. I clicked open the link to a band who appeared to have journeyed from their mountain village in Russia to busk for tourists in the city square. Three women wore long white wedding dresses, thick strands of bead necklaces, and Cossack hats that towered from their heads like minarets of black wool. They played, respectively, a cello, djembe drum, and floor tom drum. They were joined by an accordion player who could pass for a bearded hipster from Brooklyn. The accordionist was the first to sing. A bray of syllables erupted from him like an exorcism. A steady drumbeat followed and then the women commanded the singing. Their vocals ranged from yodels to yips, whoops to whispers. At first turbulence reigned, as if the women were singing different songs at each other. But soon their voices blended into a melody that curled like a river.

Left ventricular assist devices (LVADs) are mechanical pumps, which can be used to support heart failure (HF) patients as bridge to transplant and destination therapy. To automatically adjust the LVAD speed, a physiological control system needs to be designed to respond to variations of patient hemodynamics across a variety of clinical scenarios. These control systems require pressure feedback signals from the cardiovascular system. However, there are no suitable long-term implantable sensors available. In this study, a novel real-time deep convolutional neural network (CNN) for estimation of preload based on the LVAD flow was proposed. A new sensorless adaptive physiological control system for an LVAD pump was developed using the full dynamic form of model free adaptive control (FFDL-MFAC) and the proposed preload estimator to maintain the patient conditions in safe physiological ranges. The CNN model for preload estimation was trained and evaluated through 10-fold cross validation on 100 different patient conditions and the proposed sensorless control system was assessed on a new testing set of 30 different patient conditions across six different patient scenarios. The proposed preload estimator was extremely accurate with a correlation coefficient of 0.97, root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44 %, and bias of 0.29 mmHg for the testing dataset. The results also indicate that the proposed sensorless physiological controller works similarly to the preload-based physiological control system for LVAD using measured preload to prevent ventricular suction and pulmonary congestion. This study shows that the LVADs can respond appropriately to changing patient states and physiological demands without the need for additional pressure or flow measurements.

Effective conservation actions require effective population monitoring. However, accurately counting animals in the wild to inform conservation decision-making is difficult. Monitoring populations through image sampling has made data collection cheaper, wide-reaching and less intrusive but created a need to process and analyse this data efficiently. Counting animals from such data is challenging, particularly when densely packed in noisy images. Attempting this manually is slow and expensive, while traditional computer vision methods are limited in their generalisability. Deep learning is the state-of-the-art method for many computer vision tasks, but it has yet to be properly explored to count animals. To this end, we employ deep learning, with a density-based regression approach, to count fish in low-resolution sonar images. We introduce a large dataset of sonar videos, deployed to record wild mullet schools (Mugil liza), with a subset of 500 labelled images. We utilise abundant unlabelled data in a self-supervised task to improve the supervised counting task. For the first time in this context, by introducing uncertainty quantification, we improve model training and provide an accompanying measure of prediction uncertainty for more informed biological decision-making. Finally, we demonstrate the generalisability of our proposed counting framework through testing it on a recent benchmark dataset of high-resolution annotated underwater images from varying habitats (DeepFish). From experiments on both contrasting datasets, we demonstrate our network outperforms the few other deep learning models implemented for solving this task. By providing an open-source framework along with training data, our study puts forth an efficient deep learning template for crowd counting aquatic animals thereby contributing effective methods to assess natural populations from the ever-increasing visual data.

This article presents the data used to evaluate the performance of evolutionary clustering algorithm star (ECA*) compared to five traditional and modern clustering algorithms. Two experimental methods are employed to examine the performance of ECA* against genetic algorithm for clustering++ (GENCLUST++), learning vector quantisation (LVQ) , expectation maximisation (EM) , K-means++ (KM++) and K-means (KM). These algorithms are applied to 32 heterogenous and multi-featured datasets to determine which one performs well on the three tests. For one, ther paper examines the efficiency of ECA* in contradiction of its corresponding algorithms using clustering evaluation measures. These validation criteria are objective function and cluster quality measures. For another, it suggests a performance rating framework to measurethe the performance sensitivity of these algorithms on varos dataset features (cluster dimensionality, number of clusters, cluster overlap, cluster shape and cluster structure). The contributions of these experiments are two-folds: (i) ECA* exceeds its counterpart aloriths in ability to find out the right cluster number; (ii) ECA* is less sensitive towards dataset features compared to its competitive techniques. Nonetheless, the results of the experiments performed demonstrate some limitations in the ECA*: (i) ECA* is not fully applied based on the premise that no prior knowledge exists; (ii) Adapting and utilising ECA* on several real applications has not been achieved yet.

AI has the potential to revolutionize many areas of healthcare. Radiology, dermatology, and ophthalmology are some of the areas most likely to be impacted in the near future, and they have received significant attention from the broader research community. But AI techniques are now also starting to be used in in vitro fertilization (IVF), in particular for selecting which embryos to transfer to the woman. The contribution of AI to IVF is potentially significant, but must be done carefully and transparently, as the ethical issues are significant, in part because this field involves creating new people. We first give a brief introduction to IVF and review the use of AI for embryo selection. We discuss concerns with the interpretation of the reported results from scientific and practical perspectives. We then consider the broader ethical issues involved. We discuss in detail the problems that result from the use of black-box methods in this context and advocate strongly for the use of interpretable models. Importantly, there have been no published trials of clinical effectiveness, a problem in both the AI and IVF communities, and we therefore argue that clinical implementation at this point would be premature. Finally, we discuss ways for the broader AI community to become involved to ensure scientifically sound and ethically responsible development of AI in IVF.

Social norms characterize collective and acceptable group conducts in human society. Furthermore, some social norms emerge from interactions of agents or humans. To achieve agent autonomy and make norm satisfaction explainable, we include emotions into the normative reasoning process, which evaluate whether to comply or violate a norm. Specifically, before selecting an action to execute, an agent observes the environment and infer the state and consequences with its internal states after norm satisfaction or violation of a social norm. Both norm satisfaction and violation provoke further emotions, and the subsequent emotions affect norm enforcement. This paper investigates how modeling emotions affect the emergence and robustness of social norms via social simulation experiments. We find that an ability in agents to consider emotional responses to the outcomes of norm satisfaction and violation (1) promote norm compliance; and (2) improve societal welfare.

Complex systems, such as Artificial Intelligence (AI) systems, are comprised of many interrelated components. In order to represent these systems, demonstrating the relations between components is essential. Perhaps because of this, diagrams, as "icons of relation", are a prevalent medium for signifying complex systems. Diagrams used to communicate AI system architectures are currently extremely varied. The diversity in diagrammatic conceptual modelling choices provides an opportunity to gain insight into the aspects which are being prioritised for communication. In this philosophical exploration of AI systems diagrams, we integrate theories of conceptual models, communication theory, and semiotics. We discuss consequences of standardised diagrammatic languages for AI systems, concluding that while we expect engineers implementing systems to benefit from standards, researchers would have a larger benefit from guidelines.

As Deep Learning continues to drive a variety of applications in datacenters and HPC, there is a growing trend towards building large accelerators with several sub-accelerator cores/chiplets. This work looks at the problem of supporting multi-tenancy on such accelerators. In particular, we focus on the problem of mapping layers from several DNNs simultaneously on an accelerator. Given the extremely large search space, we formulate the search as an optimization problem and develop a specialized genetic algorithm called G# withcustom operators to enable structured sample-efficient exploration. We quantitatively compare G# with several common heuristics, state-of-the-art optimization methods, and reinforcement learning methods across different accelerator set-tings (large/small accelerators) and different sub-accelerator configurations (homogeneous/heterogeneous), and observeG# can consistently find better solutions. Further, to enable real-time scheduling, we also demonstrate a method to generalize the learnt schedules and transfer them to the next batch of jobs, reducing schedule compute time to near zero.