Where does your enterprise stand on the AI adoption curve? Take our AI survey to find out. It has been a great year for artificial intelligence. Companies are spending more on large AI projects, and new investment in AI startups is on pace for a record year. All this investment and spending is yielding results that are moving us all closer to the long-sought holy grail -- artificial general intelligence (AGI).

We present a new way of study of Mercer kernels, by corresponding to a special kernel $K$ a pseudo-differential operator $p({\mathbf x}, D)$ such that $\mathcal{F} p({\mathbf x}, D)^\dag p({\mathbf x}, D) \mathcal{F}^{-1}$ acts on smooth functions in the same way as an integral operator associated with $K$ (where $\mathcal{F}$ is the Fourier transform). We show that kernels defined by pseudo-differential operators are able to approximate uniformly any continuous Mercer kernel on a compact set. The symbol $p({\mathbf x}, {\mathbf y})$ encapsulates a lot of useful information about the structure of the Maximum Mean Discrepancy distance defined by the kernel $K$. We approximate $p({\mathbf x}, {\mathbf y})$ with the sum of the first $r$ terms of the Singular Value Decomposition of $p$, denoted by $p_r({\mathbf x}, {\mathbf y})$. If ordered singular values of the integral operator associated with $p({\mathbf x}, {\mathbf y})$ die down rapidly, the MMD distance defined by the new symbol $p_r$ differs from the initial one only slightly. Moreover, the new MMD distance can be interpreted as an aggregated result of comparing $r$ local moments of two probability distributions. The latter results holds under the condition that right singular vectors of the integral operator associated with $p$ are uniformly bounded. But even if this is not satisfied we can still hold that the Hilbert-Schmidt distance between $p$ and $p_r$ vanishes. Thus, we report an interesting phenomenon: the MMD distance measures the difference of two probability distributions with respect to a certain number of local moments, $r^\ast$, and this number $r^\ast$ depends on the speed with which singular values of $p$ die down.

An expert on how data and algorithms are changing work responds to Janelle Shane's "The Skeleton Crew." "The Skeleton Crew" asks us to consider two questions. The first is an interesting twist on an age-old thought experiment. But the second is more complicated, because the story invites us to become aware of a very real phenomenon and to consider what, if anything, should be done about the way the world is working for some people. The first question explores what it would mean if our machines, robots, and now artificial intelligences had feelings the way we do. "The Skeleton Crew" offers an interesting twist because the A.I. indeed has feelings just like us, because it is, in fact, us: The A.I. is a group of remote workers faking the operations of a haunted house to make it seem automated and intelligent.

"A period that had been broadly described as engagement has come to an end," Kurt Campbell, the Indo-Pacific Coordinator at the United States (US) National Security Council, told a virtual audience in May on the subject of US-China relations. "The dominant paradigm is going to be competition." On several occasions, Campbell has highlighted that one of the major arenas of this competition will concern technology. This is increasingly reflected in US national security structures. Today, there is both a senior director and coordinator for technology and national security at the White House; the National Economic Council has briefed the Cabinet on supply chain resilience; and the focus of Department of Defense policy reviews have been on emerging military technologies. The subject of intensifying technology competition is also making its way into new US avenues for cooperation with partners, including with India.

State-of-the-art process discovery methods construct free-choice process models from event logs. Consequently, the constructed models do not take into account indirect dependencies between events. Whenever the input behaviour is not free-choice, these methods fail to provide a precise model. In this paper, we propose a novel approach for enhancing free-choice process models by adding non-free-choice constructs discovered a-posteriori via region-based techniques. This allows us to benefit from the performance of existing process discovery methods and the accuracy of the employed fundamental synthesis techniques. We prove that the proposed approach preserves fitness with respect to the event log while improving the precision when indirect dependencies exist. The approach has been implemented and tested on both synthetic and real-life datasets. The results show its effectiveness in repairing models discovered from event logs.

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself. Such a stealth attack could be conducted by a mischievous, corrupt or disgruntled member of a software development team. It could also be made by those wishing to exploit a "democratization of AI" agenda, where network architectures and trained parameter sets are shared publicly. Building on work by [Tyukin et al., International Joint Conference on Neural Networks, 2020], we develop a range of new implementable attack strategies with accompanying analysis, showing that with high probability a stealth attack can be made transparent, in the sense that system performance is unchanged on a fixed validation set which is unknown to the attacker, while evoking any desired output on a trigger input of interest. The attacker only needs to have estimates of the size of the validation set and the spread of the AI's relevant latent space. In the case of deep learning neural networks, we show that a one neuron attack is possible - a modification to the weights and bias associated with a single neuron - revealing a vulnerability arising from over-parameterization. We illustrate these concepts in a realistic setting. Guided by the theory and computational results, we also propose strategies to guard against stealth attacks.

Many algorithms, whether supervised or unsupervised, make use of distance measures. These measures, such as euclidean distance or cosine similarity, can often be found in algorithms such as k-NN, UMAP, HDBSCAN, etc. Understanding the field of distance measures is more important than you might realize. Take k-NN for example, a technique often used for supervised learning. As a default, it often uses euclidean distance. However, what if your data is highly dimensional?

While the problem of spray drift is not new, it has been a significant problem in the agriculture industry for some time. Robots and machine learning technologies, which form part of the broader field of AI, have the capability to facilitate new, more sustainable agricultural methods that will take farming practices to new heights by conserving resources, minimising the use of pesticides and shortening the time to market.

The National Institute of Standards and Technology (NIST), the U.S. agency responsible for developing technical metrics to promote "innovation and industrial competitiveness," this week published a document outlining feedback and recommendations for mitigating the risk of bias in AI. The paper, about which NIST is accepting comments until August, proposes an approach for identifying and managing "pernicious" biases that can damage public trust in AI. As NIST scientist Reva Schwartz, who coauthored the paper, points out, AI is transformative in its ability to make sense of data more quickly than humans. But as AI pervades the world, it's becoming clear that its predictions can be affected by algorithmic and data biases. Making matters worse, some AI systems are built to model complex concepts that can't be directly measured by data in the first place.

Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often treat them separately, and thus develop problem-specific algorithms and their analyses. Among various exciting developments, simple SGD-type updates (potentially on multiple variables) are still prevalent in solving this class of nested problems, but they are believed to have slower convergence rate compared to that of the non-nested problems. This paper unifies several SGD-type updates for stochastic nested problems into a single SGD approach that we term ALternating Stochastic gradient dEscenT (ALSET) method. By leveraging the hidden smoothness of the problem, this paper presents a tighter analysis of ALSET for stochastic nested problems. Under the new analysis, to achieve an $\epsilon$-stationary point of the nested problem, it requires ${\cal O}(\epsilon^{-2})$ samples. Under certain regularity conditions, applying our results to stochastic compositional, min-max and reinforcement learning problems either improves or matches the best-known sample complexity in the respective cases. Our results explain why simple SGD-type algorithms in stochastic nested problems all work very well in practice without the need for further modifications.