Verification and synthesis of Cyber-Physical Systems (CPS) are challenging and still raise numerous issues so far. In this paper, an original framework with mixed sets defined as function images of symbol type domains is first proposed. Syntax and semantics are explicitly distinguished. Then, both continuous (interval) and discrete (signed, boolean) symbol types are used to model dependencies through linear and polynomial functions, so leading to mixed zonotopic and polynotopic sets. Polynotopes extend sparse polynomial zonotopes with typed symbols. Polynotopes can both propagate a mixed encoding of intervals and describe the behavior of logic gates. A functional completeness result is given, as well as an inclusion method for elementary nonlinear and switching functions. A Polynotopic Kalman Filter (PKF) is then proposed as a hybrid nonlinear extension of Zonotopic Kalman Filters (ZKF). Bridges with a stochastic uncertainty paradigm are outlined. Finally, several discrete, continuous and hybrid numerical examples including comparisons illustrate the effectiveness of the theoretical results.

This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models, which is not widely studied in the literature. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling algorithms (top-k, nucleus and tempered sampling). We focus on the task of open-ended language generation. We first show that the existing sampling algorithms have similar performance. After carefully inspecting the transformations defined by different sampling algorithms, we identify three key properties that are shared among them: entropy reduction, order preservation, and slope preservation. To validate the importance of the identified properties, we design two sets of new sampling algorithms: one set in which each algorithm satisfies all three properties, and one set in which each algorithm violates at least one of the properties. We compare their performance with existing sampling algorithms, and find that violating the identified properties could lead to drastic performance degradation, as measured by the Q-D trade-off. On the other hand, we find that the set of sampling algorithms that satisfies these properties performs on par with the existing sampling algorithms. Our data and code are available at https://github.com/moinnadeem/characterizing-sampling-algorithms

Can the powerful backpropagation of error (backprop) reinforcement learning algorithm be formulated in a manner suitable for implementation in neural circuitry? The primary challenge is to ensure that any candidate formulation uses only local information, rather than relying on global (error) signals, as in orthodox backprop. Recently several algorithms for approximating backprop using only local signals, such as predictive coding and equilibrium-prop, have been proposed. However, these algorithms typically impose other requirements which challenge biological plausibility: for example, requiring complex and precise connectivity schemes (predictive coding), or multiple sequential backwards phases with information being stored across phases (equilibrium-prop). Here, we propose a novel local algorithm, Activation Relaxation (AR), which is motivated by constructing the backpropagation gradient as the equilibrium point of a dynamical system. Our algorithm converges robustly and exactly to the correct backpropagation gradients, requires only a single type of neuron, utilises only a single backwards phase, and can perform credit assignment on arbitrary computation graphs. We illustrate these properties by training deep neural networks on visual classification tasks, and we describe simplifications to the algorithm which remove further obstacles to neurobiological implementation (for example, the weight-transport problem, and the use of nonlinear derivatives), while preserving performance.

We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared natural language output space. Unlike prior discriminative methods, our model naturally incorporates label semantics and shares knowledge across tasks. Our framework is general purpose, performing well on few-shot, low-resource, and high-resource tasks. We demonstrate these advantages on popular named entity recognition, slot labeling, and intent classification benchmarks. We set a new state-of-the-art for few-shot slot labeling, improving substantially upon the previous 5-shot ($75.0\% \rightarrow 90.9\%$) and 1-shot ($70.4\% \rightarrow 81.0\%$) state-of-the-art results. Furthermore, our model generates large improvements ($46.27\% \rightarrow 63.83\%$) in low-resource slot labeling over a BERT baseline by incorporating label semantics. We also maintain competitive results on high-resource tasks, performing within two points of the state-of-the-art on all tasks and setting a new state-of-the-art on the SNIPS dataset.

\textit{Attention} computes the dependency between representations, and it encourages the model to focus on the important selective features. Attention-based models, such as Transformers and graph attention networks (GAT) are widely utilized for sequential data and graph-structured data. This paper suggests a new interpretation and generalized structure of the attention in Transformer and GAT. For the attention in Transformer and GAT, we derive that the attention is a product of two parts: 1) the RBF kernel to measure the similarity of two instances and 2) the exponential of $L^{2}$ norm to compute the importance of individual instances. From this decomposition, we generalize the attention in three ways. First, we propose implicit kernel attention with an implicit kernel function, instead of manual kernel selection. Second, we generalize $L^{2}$ norm as the $L^{p}$ norm. Third, we extend our attention to structured multi-head attention. Our generalized attention shows better performance on classification, translation, and regression tasks.

International organizations and corporations are racing to develop global guidelines for the ethical use of artificial intelligence. Declarations, manifestos, and recommendations are flooding the internet. But these efforts will be futile if they fail to account for the cultural and regional contexts in which AI operates. AI systems have repeatedly been shown to cause problems that disproportionately affect marginalized groups while benefiting a privileged few. The global AI ethics efforts under way today--of which there are dozens--aim to help everyone benefit from this technology, and to prevent it from causing harm.

Walmart has had drone delivery ambitions for years now, and today they've announced a partnership with Zipline for on-demand delivery of "health and wellness" products. Zipline drones aren't the quadcopters that most think of for these types of delivery services. Instead, they're gliders that have longer range and won't just drop out of the sky if something fails. Trial deliveries using Zipline's drones will take place near Walmart headquarters in northwest Arkansas with a plan to start early next year. Walmart says that the Zipline drones will be able to operate within a 50-mile radius, and they produce no carbon emissions.

With telcos and enterprises alike fast tracking their digitalisation initiatives across the region, the Middle East finds itself on the cutting edge when it comes to digital innovation. In the Gulf Cooperation Council (GCC), the launch of 5G will bring a plethora of opportunities for enterprises to redefine the way they do business and deliver a diverse portfolio of digital services and products to an increasingly demanding client base. Similarly, across the greater Middle East and Africa region, the proliferation of 4G and LTE networks is kick starting a digital revolution that will fundamentally change the way people live their lives – opening up a veritable smorgasbord of digital opportunities, from remote working and e-learning initiatives, to mobile financial applications and e-health solutions. As telcos continue to evolve their product offering way beyond the mere provision of "dumb pipe" connectivity, they will increasingly look to leverage partnerships with service providers who can facilitate their own digitalisation on an end-to-end basis. Most of the world's biggest and most ambitious digital transformation champions are looking to sharpen their focus on the Middle East and Africa region.

SingularityU South Africa has announced the first 40 speakers who will address Africa at the SingularityU South Africa Summit Online on October 14 and 15 2020. The line-up includes thought leaders from across the globe, and includes sought-after South African captains of industry. True to the SingularityU prowess of demystifying exponential technologies and their potential to solve the global grand challenges, the world's top innovators will share their latest insights. American neuroscientist Vivienne Ming and founder of Socos Labs will address how artificial intelligence can make us better humans. Australian AI expert Kellie Nuttall will speak about artificial intelligence and the future of work, while South African technology pioneer Andile Ngcaba will share how artificial intelligence can effectively be used by governments; LinkedIn's top voice in tech Cathy Hackl will explain the impact of emerging technologies on business.

This document describes Pilot, our submission for Human-Agent Negotiation Challenge at IJCAI 2020. Pilot is a virtual human that participates in a sequence of three negotiations with a human partner. Our system is based on the Interactive Arbitration Guide Online (IAGO) negotiation framework. We leverage prior Affective Computing and Psychology research in negotiations to guide various key principles that define the behavior and personality of our agent. Pilot has been selected as one of the finalists for presentation at IJCAI.