It is going to be interesting to see how society deals with artificial intelligence, but it will definitely be cool. Artificial intelligence (AI) can be defined to mean the use of intelligent machines to replicate and augment the intelligence of human beings. The Turing test was propounded to show what factors determine whether a machine operates on artificial intelligence or not. AI applications are being used in various fields such as telecommunication, banking, agriculture, manufacturing, health care, and transportation. The implementation of AI in health care aims to enhance the lives of the patients and enable physicians, doctors, hospitals, and administrators to improve health care delivery in a cost-effective and time-efficient manner. The traditional drug industry is also experiencing a wave of change due to the implementation of AI-based processes in drug discovery and development. Substitution of AI technology-based solutions in place of the traditional methods for drug discovery is expected to reduce the time for drug development. Using AI in clinical trials has reduced the time required for drug trials from 4–6 months to three months. After the analysis of the genomic data from different patients, AI helps by selecting only those patients whose genetic profile suggests it will help them to undergo testing in the clinical trial.2 Machine learning technologies, deep learning algorithms, various neural networks (such as artificial neural networks or computational neural networks), and content screening are a few examples of AI that have brought radical changes to the process of drug discovery and development.

At the beginning of 2021, the European Commission will propose legislation on AI that will be, at first instance, horizontal (as opposed to sectoral) and risk-based, with mandatory requirements for high-risk AI applications. The new rules will aim at ensuring transparency, accountability and consumer protection, including safety, through robust AI governance and data quality requirements. Europe's approach to regulating technology is based on the precautionary principle, which enables rapid regulatory intervention in the face of possible danger to human, animal or plant health, or to protect the environment. This perspective has helped Europe to become a global leader in the shaping of the digital technology market. Particularly, with the introduction of the General Data Protection Regulation (GDPR) in 2018, Europe considers it has gained a competitive advantage through the creation of a trust mark for increased privacy protection. Australia and New Zealand have a close relationship with the European Union (EU) and its member countries historically.

In April 2020, Amazon, the world's wealthiest technology company, received a shipment of 1,500 heat-mapping camera systems from the Chinese surveillance company Dahua. Many of these systems will be installed in Amazon warehouses to monitor the heat signatures of employees and alert managers if workers exhibit Covid-19-like symptoms. Other cameras included in the shipment will be distributed to IBM and Chrysler, among other buyers. While Amazon's move to protect workers from Covid-19 is welcome, it acquired this technology from a company from a company researchers have shown is involved in human rights abuses. As Sanjana Varghese noted recently, the "humanitarian experimentation" work in pandemic surveillance of companies like Dahua doubles as technologies of population management.

When Amanda Kemper found out that artificial intelligence would help monitor students during her mechanical engineering class's final exam this summer, she was worried. Like many students, Kemper's classes at the University of Wisconsin-Madison shifted online suddenly in the spring due to the ongoing pandemic. With remote learning came remote exams: Starting in July, the university let instructors use software from Honorlock, which is one of numerous companies that can record video -- and much more -- of students as they take tests, and uses AI to point out any behavior that looks like cheating. Kemper learned about Honorlock a week before her final exam and she had a number of concerns. She didn't like the idea of being recorded and having that recording sent to her professor.

Emerging applications of machine learning in numerous areas involve continuous gathering of and learning from streams of data. Real-time incorporation of streaming data into the learned models is essential for improved inference in these applications. Further, these applications often involve data that are either inherently gathered at geographically distributed entities or that are intentionally distributed across multiple machines for memory, computational, and/or privacy reasons. Training of models in this distributed, streaming setting requires solving stochastic optimization problems in a collaborative manner over communication links between the physical entities. When the streaming data rate is high compared to the processing capabilities of compute nodes and/or the rate of the communications links, this poses a challenging question: how can one best leverage the incoming data for distributed training under constraints on computing capabilities and/or communications rate? A large body of research has emerged in recent decades to tackle this and related problems. This paper reviews recently developed methods that focus on large-scale distributed stochastic optimization in the compute- and bandwidth-limited regime, with an emphasis on convergence analysis that explicitly accounts for the mismatch between computation, communication and streaming rates. In particular, it focuses on methods that solve: (i) distributed stochastic convex problems, and (ii) distributed principal component analysis, which is a nonconvex problem with geometric structure that permits global convergence. For such methods, the paper discusses recent advances in terms of distributed algorithmic designs when faced with high-rate streaming data. Further, it reviews guarantees underlying these methods, which show there exist regimes in which systems can learn from distributed, streaming data at order-optimal rates.

Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a set of interpretable features for downstream analysis is needed, a key requirement for many scientific investigations. We present an algorithm and training paradigm designed specifically to address this: decontextualized hierarchical representation learning (DHRL). By combining a generative model chaining procedure with a ladder network architecture and latent space regularization for inference, DHRL address the limitations of small datasets and encourages a disentangled set of hierarchically organized features. In addition to providing a tractable path for analyzing complex hierarchal patterns using variation inference, this approach is generative and can be directly combined with empirical and theoretical approaches. To highlight the extensibility and usefulness of DHRL, we demonstrate this method in application to a question from evolutionary biology.

Proximities are at the heart of almost all machine learning methods. If the input data are given as numerical vectors of equal lengths, euclidean distance, or a Hilbertian inner product is frequently used in modeling algorithms. In a more generic view, objects are compared by a (symmetric) similarity or dissimilarity measure, which may not obey particular mathematical properties. This renders many machine learning methods invalid, leading to convergence problems and the loss of guarantees, like generalization bounds. In many cases, the preferred dissimilarity measure is not metric, like the earth mover distance, or the similarity measure may not be a simple inner product in a Hilbert space but in its generalization a Krein space. If the input data are non-vectorial, like text sequences, proximity-based learning is used or ngram embedding techniques can be applied. Standard embeddings lead to the desired fixed-length vector encoding, but are costly and have substantial limitations in preserving the original data's full information. As an information preserving alternative, we propose a complex-valued vector embedding of proximity data. This allows suitable machine learning algorithms to use these fixed-length, complex-valued vectors for further processing. The complex-valued data can serve as an input to complex-valued machine learning algorithms. In particular, we address supervised learning and use extensions of prototype-based learning. The proposed approach is evaluated on a variety of standard benchmarks and shows strong performance compared to traditional techniques in processing non-metric or non-psd proximity data.

Abstract--Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, achieving practical speedups on GPUs is difficult because these applications have relatively moderate levels of sparsity that are not sufficient for existing sparse kernels to outperform their dense counterparts. In this work, we study sparse matrices from deep learning applications and identify favorable properties that can be exploited to accelerate computation. Based on these insights, we develop high-performance GPU kernels for two sparse matrix operations widely applicable in neural networks: sparse matrix-dense matrix multiplication and sampled dense-dense matrix multiplication. Using our kernels, we demonstrate sparse Transformer and MobileNet models that achieve 1.2-2.1 speedups and up to 12.8 memory savings without sacrificing accuracy. This work enables speedups for all problems in the highlighted region. Existing GPU kernels for sparse linear algebra are procedure, a sparsification algorithm is applied to produce a primarily optimized for scientific applications, where matrices neural network where a high fraction of the weights are zerovalued are extremely (99%) sparse. The weight matrices can then be stored in levels of sparsity found in deep neural networks, these kernels a compressed format, and sparse linear algebra kernels can be are not able to outperform their dense counterparts. In the context of generative To address this issue, structure can be enforced on the models, sparsity has been applied to reduce the computational topology of nonzeros such that nonzero values are grouped requirements of self-attention in Transformer architectures [6], into blocks [12]-[14]. While this approach is able to recover [10], [11].

Strategic argumentation provides a simple model of disputation and negotiation among agents. Although agents might be expected to act in our best interests, there is little that enforces such behaviour. (Maher, 2016) introduced a model of corruption and resistance to corruption within strategic argumentation. In this paper we identify corrupt behaviours that are not detected in that formulation. We strengthen the model to detect such behaviours, and show that, under the strengthened model, all the strategic aims in (Maher, 2016) are resistant to corruption.

In this paper we describe a concept-wise multi-preference semantics for description logic which has its root in the preferential approach for modeling defeasible reasoning in knowledge representation. We argue that this proposal, beside satisfying some desired properties, such as KLM postulates, and avoiding the drowning problem, also defines a plausible notion of semantics. We motivate the plausibility of the concept-wise multi-preference semantics by developing a logical semantics of self-organising maps, which have been proposed as possible candidates to explain the psychological mechanisms underlying category generalisation, in terms of multi-preference interpretations.