In this paper, we investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image classifier ensembles. We investigate the potential of an attribution-based diversity metric to improve the known accuracy-diversity trade-off of the typical prediction-based diversity. Our motivation is based on analytical studies of design diversity that have shown that a reduction of common failure modes is possible if diversity of design choices is achieved. Using ResNet50 as a comparison baseline, we evaluate the resiliency of multiple individual DL model architectures against dataset distribution shifts corresponding to natural image corruptions. We compare ensembles created with diverse model architectures trained either independently or through a Neural Architecture Search technique and evaluate the correlation of prediction-based and attribution-based diversity to the final ensemble accuracy. We evaluate a set of diversity enforcement heuristics based on negative correlation learning to assess the final ensemble resilience to natural image corruptions and inspect the resulting prediction, activation, and attribution diversity. Our key observations are: 1) model architecture is more important for resiliency than model size or model accuracy, 2) attribution-based diversity is less negatively correlated to the ensemble accuracy than prediction-based diversity, 3) a balanced loss function of individual and ensemble accuracy creates more resilient ensembles for image natural corruptions, 4) architecture diversity produces more diversity in all explored diversity metrics: predictions, attributions, and activations.

Existing question-answering research focuses on unanswerable questions in the context of always providing an answer when a system can\dots but what about cases where a system {\bf should not} answer a question. This can either be to protect sensitive users or sensitive information. Many models expose sensitive information under interrogation by an adversarial user. We seek to determine if it is possible to teach a question-answering system to keep a specific fact secret. We design and implement a proof-of-concept architecture and through our evaluation determine that while possible, there are numerous directions for future research to reduce system paranoia (false positives), information leakage (false negatives) and extend the implementation of the work to more complex problems with preserving secrecy in the presence of information aggregation.

Content-based image retrieval is the process of retrieving a subset of images from an extensive image gallery based on visual contents, such as color, shape or spatial relations, and texture. In some applications, such as localization, image retrieval is employed as the initial step. In such cases, the accuracy of the top-retrieved images significantly affects the overall system accuracy. The current paper introduces a simple yet efficient image retrieval system with a fewer trainable parameters, which offers acceptable accuracy in top-retrieved images. The proposed method benefits from a dilated residual convolutional neural network with triplet loss. Experimental evaluations show that this model can extract richer information (i.e., high-resolution representations) by enlarging the receptive field, thus improving image retrieval accuracy without increasing the depth or complexity of the model. To enhance the extracted representations' robustness, the current research obtains candidate regions of interest from each feature map and applies Generalized-Mean pooling to the regions. As the choice of triplets in a triplet-based network affects the model training, we employ a triplet online mining method. We test the performance of the proposed method under various configurations on two of the challenging image-retrieval datasets, namely Revisited Paris6k (RPar) and UKBench. The experimental results show an accuracy of 94.54 and 80.23 (mean precision at rank 10) in the RPar medium and hard modes and 3.86 (recall at rank 4) in the UKBench dataset, respectively.

AI isn't just good for writing term papers or clickbait financial explainers; it could help save lives in the medical field. At Google's annual The Check Up healthcare event, it announced AI-related partnerships for ultrasound readings, medical language models and cancer treatments -- areas where the technology could someday serve as a force for good. Google sees AI as crucial in reading ultrasound devices in regions without enough trained specialists. Although the sensors are more accessible than ever, they require experts to conduct exams and interpret images. The company's AI models could help simplify that process by identifying data like the early detection of breast cancer and gestational age in expectant mothers.

Some 540 million years ago, diverse life forms suddenly began to emerge from the muddy ocean floors of planet Earth. This period is known as the Cambrian Explosion, and these aquatic critters are our ancient ancestors. All complex life on Earth evolved from these underwater creatures. Scientists believe all it took was an ever-so-slight increase in ocean oxygen levels above a certain threshold. We may now be in the midst of a Cambrian Explosion for artificial intelligence (AI). In the past few years, a burst of incredibly capable AI programs like Midjourney, DALL-E 2 and ChatGPT have showcased the rapid progress we've made in machine learning.

As AI technology like ChatGPT evolves, so do the strategies and tactics used by cybercriminals. Steve Flynn, Sales and Marketing Director at ESET Southern Africa, says ongoing awareness is crucial in understanding how to manage potential cybersecurity challenges posed by these developing tools. As artificial intelligence (AI) technology becomes a new reality for individuals and businesses, its potential impact on cybersecurity cannot be ignored. OpenAI and its language model, ChatGPT, are no exception and while these tools offer significant benefits to almost every industry, they also present new challenges for digital security. ChatGPT raises concerns due to its natural language processing capabilities, which could be used to create highly personalised and sophisticated cyberattacks.

The COVID-19 pandemic was a shock to higher education systems everywhere. But while some changes, like moving lectures online, were relatively easy to make, assessment posed a much bigger challenge. Assessment can take many forms, from essays to exams to experiments and more. They increased their use of programs like Turnitin to check for matched wording in students' assignments. And for closed-book, timed tests they used tools such as Proctorio, which monitor a student's computer or phone while they write exams.

Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and "smooth") model was shown to elongate the time-to-failure $t_\textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{\textrm{failure}} \propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $\left(t_{\textrm{failure}} \propto N^{-0.29}\right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia.

Given the strong results of self-supervised models on various tasks, there have been surprisingly few studies exploring self-supervised representations for acoustic word embeddings (AWE), fixed-dimensional vectors representing variable-length spoken word segments. In this work, we study several pre-trained models and pooling methods for constructing AWEs with self-supervised representations. Owing to the contextualized nature of self-supervised representations, we hypothesize that simple pooling methods, such as averaging, might already be useful for constructing AWEs. When evaluating on a standard word discrimination task, we find that HuBERT representations with mean-pooling rival the state of the art on English AWEs. More surprisingly, despite being trained only on English, HuBERT representations evaluated on Xitsonga, Mandarin, and French consistently outperform the multilingual model XLSR-53 (as well as Wav2Vec 2.0 trained on English).

Multi-view clustering has been widely used in recent years in comparison to single-view clustering, for clear reasons, as it offers more insights into the data, which has brought with it some challenges, such as how to combine these views or features. Most of recent work in this field focuses mainly on tensor representation instead of treating the data as simple matrices. This permits to deal with the high-order correlation between the data which the based matrix approach struggles to capture. Accordingly, we will examine and compare these approaches, particularly in two categories, namely graph-based clustering and subspace-based clustering. We will conduct and report experiments of the main clustering methods over a benchmark datasets.