A world-first Monash University study has found using artificial intelligence into aged care homes can exacerbate ageism and social inequality. The paper, published in the Journal of Applied Gerontology, reveals the unmet value of artificial intelligence (AI) to help solve aged care issues including loneliness of residents through chat, video and image sharing, through to medical diagnosis and assessments tools. The study found pushing AI technology - from robots to voice assistants - into aged care can exacerbate ageist views due to the choices of carers on how best to use technology for older people in these settings. "AI can perpetuate ageism and exacerbate existing social inequalities," lead author Dr Barbara Barbosa Neves said. "When implementing AI technologies in aged care, we must consider them as part of a suite of care services and not as isolated solutions."

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.

This paper presents a novel approach to solve simultaneously the problems of human activity recognition and whole-body motion and dynamics prediction for real-time applications. Starting from the dynamics of human motion and motor system theory, the notion of mixture of experts from deep learning has been extended to address this problem. In the proposed approach, experts are modelled as a sequence-to-sequence recurrent neural networks (RNN) architecture. Experiments show the results of 66-DoF real-world human motion prediction and action recognition during different tasks like walking and rotating. The code associated with this paper is available at: \url{github.com/ami-iit/paper_darvish_2022_humanoids_action-kindyn-predicition}

Large Language Models (LLMs) have demonstrated impressive text generation capabilities, prompting us to reconsider the future of human-AI co-creation and how humans interact with LLMs. In this paper, we present a spectrum of content generation tasks and their corresponding human-AI interaction patterns. These tasks include: 1) fixed-scope content curation tasks with minimal human-AI interactions, 2) independent creative tasks with precise human-AI interactions, and 3) complex and interdependent creative tasks with iterative human-AI interactions. We encourage the generative AI and HCI research communities to focus on the more complex and interdependent tasks, which require greater levels of human involvement.

Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this property to create random fractal images for model pre-training. In this paper, we study the inverse problem -- given a target image (not necessarily a fractal), we aim to generate a fractal image that looks like it. We propose a novel approach that learns the parameters underlying a fractal image via gradient descent. We show that our approach can find fractal parameters of high visual quality and be compatible with different loss functions, opening up several potentials, e.g., learning fractals for downstream tasks, scientific understanding, etc.

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various downstream natural language tasks simply by including concatenated training examples of these tasks in its input. Though disruptive for many practical applications of large language models, this emergent learning paradigm is not well understood from a theoretical perspective. In this paper, we propose a first-of-its-kind PAC based framework for in-context learnability, and use it to provide the first finite sample complexity results for the in-context learning setup. Our framework includes an initial pretraining phase, which fits a function to the pretraining distribution, and then a second in-context learning phase, which keeps this function constant and concatenates training examples of the downstream task in its input. We use our framework in order to prove that, under mild assumptions, when the pretraining distribution is a mixture of latent tasks (a model often considered for natural language pretraining), these tasks can be efficiently learned via in-context learning, even though the model's weights are unchanged and the input significantly diverges from the pretraining distribution. Our theoretical analysis reveals that in this setting, in-context learning is more about identifying the task than about learning it, a result which is in line with a series of recent empirical findings. We hope that the in-context learnability framework presented in this paper will facilitate future progress towards a deeper understanding of this important new learning paradigm.

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level accurately.

In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information contained in the dataset may lead to unsatisfactory recovery performance. To address this limitation, we make efforts to excavate the essential label relevant information to improve the recovery performance. Our method formulates the LE problem as the following two joint processes: 1) learning the representation with the essential label relevant information, 2) recovering label distributions based on the learned representation. The label relevant information can be excavated based on the "bottleneck" formed by the learned representation. Significantly, both the label relevant information about the label assignments and the label relevant information about the label gaps can be explored in our method. Evaluation experiments conducted on several benchmark label distribution learning datasets verify the effectiveness and competitiveness of LIB. Our source codes are available https://github.com/qinghai-zheng/LIBLE

The feature matching is a basic step in matching different datasets. This article proposes shows a new hybrid model of a pretrained Natural Language Processing (NLP) based model called BERT used in parallel with a statistical model based on Jaccard similarity to measure the similarity between list of features from two different datasets. This reduces the time required to search for correlations or manually match each feature from one dataset to another. NTRODUCTION The features matching is a first step in many of the data processes. It plays a crucial part in data fusion process.

Previous work has demonstrated that words are hyperarticulated on dimensions of speech that differentiate them from a minimal pair competitor. This phenomenon has been termed contrastive hyperarticulation (CH). We present a dynamic neural field (DNF) model of voice onset time (VOT) planning that derives CH from an inhibitory influence of the minimal pair competitor during planning. We test some predictions of the model with a novel experiment investigating CH of voiceless stop consonant VOT in pseudowords. The results demonstrate a CH effect in pseudowords, consistent with a basis for the effect in the real-time planning and production of speech. The scope and magnitude of CH in pseudowords was reduced compared to CH in real words, consistent with a role for interactive activation between lexical and phonological levels of planning. We discuss the potential of our model to unify an apparently disparate set of phenomena, from CH to phonological neighborhood effects to phonetic trace effects in speech errors.