One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons. It seems evident that accurate interpretations thereof would provide insights into the question what a deep learning system has internally \emph{detected} as relevant on the input, thus lifting some of the black box character of deep learning systems. The state of the art on this front indicates that hidden node activations appear to be interpretable in a way that makes sense to humans, at least in some cases. Yet, systematic automated methods that would be able to first hypothesize an interpretation of hidden neuron activations, and then verify it, are mostly missing. In this paper, we provide such a method and demonstrate that it provides meaningful interpretations. It is based on using large-scale background knowledge -- a class hierarchy of approx. 2 million classes curated from the Wikipedia Concept Hierarchy -- together with a symbolic reasoning approach called \emph{concept induction} based on description logics that was originally developed for applications in the Semantic Web field. Our results show that we can automatically attach meaningful labels from the background knowledge to individual neurons in the dense layer of a Convolutional Neural Network through a hypothesis and verification process.

Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications. The majority of currently known topological materials have been discovered using methods that involve symmetry-based analysis of the quantum wavefunction. Here we use machine learning to develop a simple-to-use heuristic chemical rule that diagnoses with a high accuracy whether a material is topological using only its chemical formula. This heuristic rule is based on a notion that we term topogivity, a machine-learned numerical value for each element that loosely captures its tendency to form topological materials. We next implement a high-throughput procedure for discovering topological materials based on the heuristic topogivity-rule prediction followed by ab initio validation. This way, we discover new topological materials that are not diagnosable using symmetry indicators, including several that may be promising for experimental observation.

Abstract--In distributed multiple-input multiple-output (D-allocate their power among users to optimize the system's To overcome the complexity problem, Bashar et al. [3] In this study, we investigate the potential effects of adversarial attacks targeting AI-driven power control systems in I. We explain the main constraints of the adversary Deep learning is expected to be an important enabler for resulting from the distributed nature of wireless domain and many wireless communication challenges in 6G. Deep neural focus only on the possible practical scenarios to observe the networks (DNNs) are being proposed to handle a wide range severity of adversarial attack threats. We work on attacks based of wireless communication tasks including encoding/decoding on universal adversarial perturbation (UAP) which are not operations, spectrum sensing and RF signal classification. We propose a novel modified UAP (m-D-MIMO is a new network type considered for 6G communication UAP) technique that crafts a specific perturbation for each systems where many radio units (RUs) are geographically input where there is only a partial knowledge about some of distributed in a region to increase the coverage input entries.

Artificial intelligence (AI) technologies are widely deployed in smartphone photography; and prompt-based image synthesis models have rapidly become commonplace. In this paper, we describe a Research-through-Design (RtD) project which explores this shift in the means and modes of image production via the creation and use of the Entoptic Field Camera. Entoptic phenomena usually refer to perceptions of floaters or bright blue dots stemming from the physiological interplay of the eye and brain. We use the term entoptic as a metaphor to investigate how the material interplay of data and models in AI technologies shapes human experiences of reality. Through our case study using first-person design and a field study, we offer implications for critical, reflective, more-than-human and ludic design to engage AI technologies; the conceptualisation of an RtD research space which contributes to AI literacy discourses; and outline a research trajectory concerning materiality and design affordances of AI technologies.

The Winograd Schema Challenge - a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge - was proposed by Hector Levesque in 2011. By 2019, a number of AI systems, based on large pre-trained transformer-based language models and fine-tuned on these kinds of problems, achieved better than 90% accuracy. In this paper, we review the history of the Winograd Schema Challenge and discuss the lasting contributions of the flurry of research that has taken place on the WSC in the last decade. We discuss the significance of various datasets developed for WSC, and the research community's deeper understanding of the role of surrogate tasks in assessing the intelligence of an AI system.

Fluent human-human teaming is often characterized by tacit interaction without explicit communication. This is because explicit communication, such as language utterances and gestures, are inherently interruptive. On the other hand, tacit interaction requires team situation awareness (TSA) to facilitate, which often relies on explicit communication to maintain, creating a paradox. In this paper, we consider implicit and naturalistic team status projection for tacit human-robot interaction. Implicitness minimizes interruption while naturalness reduces cognitive demand, and they together improve responsiveness to robots. We introduce a novel process for such Team status Projection via virtual Shadows, or TPS. We compare our method with two baselines that use explicit projection for maintaining TSA. Results via human factors studies demonstrate that TPS provides a more fluent human-robot interaction experience by significantly improving human responsiveness to robots in tacit teaming scenarios, which suggests better TSA. Participants acknowledged robots implementing TPS as more acceptable as a teammate and favorable. Simultaneously, we demonstrate that TPS is comparable to, and sometimes better than, the best-performing baseline in maintaining accurate TSA

The problem of perimeter defense games considers a scenario where the defenders are constrained to move along a perimeter and try to capture the intruders while the intruders aim to reach the perimeter without being captured by the defenders (Shishika and Kumar, 2020). A number of previous works have solved this problem with engagements on a planar game space (Shishika and Kumar, 2018; Chen et al., 2021). However, in the real world, the perimeter may be represented by a three-dimensional shape as the players (e.g., defenders and intruders) may have the ability to perform three-dimensional motions. For example, a perimeter of a building that defenders aim to protect can be enclosed by a hemisphere. As a result, the defender robots should be able to move in three-dimensional space. For example, aerial robots have been well studied in various settings (Chen et al., 2020; Nguyen et al., 2019; Lee et al., 2016, 2020a), and all these settings can be real-world use-cases for perimeter defense. For instance, intruders try to attack a military base in the forest and defenders aim to capture the intruders. In this work, we tackle the perimeter defense problem in a domain where multiple agents collaborate to accomplish a task. Multi-agent collaboration has been explored in many areas including environmental mapping (Liu et al., 2022; Thrun et al., 2000), search and rescue (Miller et al., 2020; Baxter et al., 2007),

Industrial Internet of Things (I-IoT) is a collaboration of devices, sensors, and networking equipment to monitor and collect data from industrial operations. Machine learning (ML) methods use this data to make high-level decisions with minimal human intervention. Data-driven predictive maintenance (PDM) is a crucial ML-based I-IoT application to find an optimal maintenance schedule for industrial assets. The performance of these ML methods can seriously be threatened by adversarial attacks where an adversary crafts perturbed data and sends it to the ML model to deteriorate its prediction performance. The models should be able to stay robust against these attacks where robustness is measured by how much perturbation in input data affects model performance. Hence, there is a need for effective defense mechanisms that can protect these models against adversarial attacks. In this work, we propose a double defense mechanism to detect and mitigate adversarial attacks in I-IoT environments. We first detect if there is an adversarial attack on a given sample using novelty detection algorithms. Then, based on the outcome of our algorithm, marking an instance as attack or normal, we select adversarial retraining or standard training to provide a secondary defense layer. If there is an attack, adversarial retraining provides a more robust model, while we apply standard training for regular samples. Since we may not know if an attack will take place, our adaptive mechanism allows us to consider irregular changes in data. The results show that our double defense strategy is highly efficient where we can improve model robustness by up to 64.6% and 52% compared to standard and adversarial retraining, respectively.

Many companies are simply experimenting with AI and don't plan or budget for full deployment of AI systems. This typically occurs because the projects aren't accorded sufficient resources, scope, and time. The most aggressive adoption, combined with the best integration with strategy and operations, will ultimately provide the greatest business value. If you ask someone to name a company that's putting artificial intelligence at the center of its business, you'll probably hear a predictable list of technology powerhouses: Alphabet (Google), Meta (Facebook), Amazon, Microsoft, Tencent, and Alibaba. But at legacy organizations in other industries many leaders feel that it's beyond the capabilities of their companies to transform themselves using AI. Because this technology is relatively new, however, no company was powered by AI a decade ago, so all those that have been successful had to accomplish the same fundamental tasks: They put people in charge of creating the AI; they rounded up the required data, talent, and monetary investments; and they moved as aggressively as possible to build capabilities. At many organizations AI initiatives are too small and too tentative; they never get to the only step that can add economic value--deploying a model on a large scale. In a 2019 survey conducted by MIT Sloan Management Review and Boston Consulting Group, seven out of 10 companies reported that their AI efforts had had minimal or no impact. The same survey showed that among the 90% of companies that had made some investment in AI, fewer than 40% had achieved business gains over the previous three years.

After a long hiatus, "Saturday Night Live" returned with guest host Aubrey Plaza and musical guest Sam Smith. In the 10th episode of Season 48, the NBC sketch comedy show wasted no time in mocking congressman George Santos, the embattled New York Republican who for weeks has generated headlines over false statements about his background. The episode also featured cameos from President Joe Biden and former cast member Amy Poehler. Other cameos included actress Allison Williams, along with Jonathan and Drew Scott, otherwise known as the "Property Brothers," as well as skateboard legend Tony Hawk. German singer Kim Petras joined Smith in the first musical segment and actress Sharon Stone appeared in Smith's second performance.