Artificial intelligence (AI) has the potential to revolutionize the drug discovery process, offering improved efficiency, accuracy, and speed. However, the successful application of AI is dependent on the availability of high-quality data, the addressing of ethical concerns, and the recognition of the limitations of AI-based approaches. In this article, the benefits, challenges and drawbacks of AI in this field are reviewed, and possible strategies and approaches for overcoming the present obstacles are proposed. The use of data augmentation, explainable AI, and the integration of AI with traditional experimental methods, as well as the potential advantages of AI in pharmaceutical research are also discussed. Overall, this review highlights the potential of AI in drug discovery and provides insights into the challenges and opportunities for realizing its potential in this field. Note from the human-authors: This article was created to test the ability of ChatGPT, a chatbot based on the GPT-3.5 language model, to assist human authors in writing review articles. The text generated by the AI following our instructions (see Supporting Information) was used as a starting point, and its ability to automatically generate content was evaluated. After conducting a thorough review, human authors practically rewrote the manuscript, striving to maintain a balance between the original proposal and scientific criteria. The advantages and limitations of using AI for this purpose are discussed in the last section.

Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern. An effective solution to this problem is to train models with differential privacy, which provides rigorous privacy guarantees by injecting random noise to the gradients. This paper focuses on the scenario where sensitive data are distributed among multiple participants, who jointly train a model through federated learning (FL), using both secure multiparty computation (MPC) to ensure the confidentiality of each gradient update, and differential privacy to avoid data leakage in the resulting model. A major challenge in this setting is that common mechanisms for enforcing DP in deep learning, which inject real-valued noise, are fundamentally incompatible with MPC, which exchanges finite-field integers among the participants. Consequently, most existing DP mechanisms require rather high noise levels, leading to poor model utility. Motivated by this, we propose Skellam mixture mechanism (SMM), an approach to enforce DP on models built via FL. Compared to existing methods, SMM eliminates the assumption that the input gradients must be integer-valued, and, thus, reduces the amount of noise injected to preserve DP. Further, SMM allows tight privacy accounting due to the nice composition and sub-sampling properties of the Skellam distribution, which are key to accurate deep learning with DP. The theoretical analysis of SMM is highly non-trivial, especially considering (i) the complicated math of differentially private deep learning in general and (ii) the fact that the mixture of two Skellam distributions is rather complex, and to our knowledge, has not been studied in the DP literature. Extensive experiments on various practical settings demonstrate that SMM consistently and significantly outperforms existing solutions in terms of the utility of the resulting model.

The reviews of customers play an essential role in online shopping. People often refer to reviews or comments of previous customers to decide whether to buy a new product. Catching up with this behavior, some people create untruths and illegitimate reviews to hoax customers about the fake quality of products. These are called spam reviews, confusing consumers on online shopping platforms and negatively affecting online shopping behaviors. We propose the dataset called ViSpamReviews, which has a strict annotation procedure for detecting spam reviews on e-commerce platforms. Our dataset consists of two tasks: the binary classification task for detecting whether a review is spam or not and the multi-class classification task for identifying the type of spam. The PhoBERT obtained the highest results on both tasks, 86.89%, and 72.17%, respectively, by macro average F1 score.

Current software documentation practices don't adequately serve developers. The ultimate goal of software documentation is to help developers find and fix code quickly and efficiently. Still, in most cases, code comments are difficult to understand, incomplete, out of date and untrustworthy to many developers, often resulting in significant additional work and unintended business risks. Traditionally, supplying detailed documentation and comments in code can help developers quickly get the context surrounding the code they are working on, resulting in increased productivity. While documentation and comments are an important part of software engineering, poor or insufficient documentation is a widespread problem that can ultimately create more problems for developers and negatively impact the business.

This article provides a comprehensive overview of the main ethical issues related to the impact of Artificial Intelligence (AI) on human society. AI is the use of machines to do things that would normally require human intelligence. In many areas of human life, AI has rapidly and significantly affected human society and the ways we interact with each other. It will continue to do so. Along the way, AI has presented substantial ethical and socio-political challenges that call for a thorough philosophical and ethical analysis. Its social impact should be studied so as to avoid any negative repercussions. AI systems are becoming more and more autonomous, apparently rational, and intelligent. This comprehensive development gives rise to numerous issues. In addition to the potential harm and impact of AI technologies on our privacy, other concerns include their moral and legal status (including moral and legal rights), their possible moral agency and patienthood, and issues related to their possible personhood and even dignity. It is common, however, to distinguish the following issues as of utmost significance with respect to AI and its relation to human society, according to three different time periods: (1) short-term (early 21st century): autonomous systems (transportation, weapons), machine bias in law, privacy and surveillance, the black box problem and AI decision-making; (2) mid-term (from the 2040s to the end of the century): AI governance, confirming the moral and legal status of intelligent machines (artificial moral agents), human-machine interaction, mass automation; (3) long-term (starting with the 2100s): technological singularity, mass unemployment, space colonisation. This section discusses why AI is of utmost importance for our systems of ethics and morality, given the increasing human-machine interaction. AI may mean several different things and it is defined in many different ways. When Alan Turing introduced the so-called Turing test (which he called an'imitation game') in his famous 1950 essay about whether machines can think, the term'artificial intelligence' had not yet been introduced. Turing considered whether machines can think, and suggested that it would be clearer to replace that question with the question of whether it might be possible to build machines that could imitate humans so convincingly that people would find it difficult to tell whether, for example, a written message comes from a computer or from a human (Turing 1950). The term'AI' was coined in 1955 by a group of researchers--John McCarthy, Marvin L. Minsky, Nathaniel Rochester and Claude E. Shannon--who organised a famous two-month summer workshop at Dartmouth College on the'Study of Artificial Intelligence' in 1956. This event is widely recognised as the very beginning of the study of AI.

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models

Machine reading comprehension (MRC) is a long-standing topic in natural language processing (NLP). The MRC task aims to answer a question based on the given context. Recently studies focus on multi-hop MRC which is a more challenging extension of MRC, which to answer a question some disjoint pieces of information across the context are required. Due to the complexity and importance of multi-hop MRC, a large number of studies have been focused on this topic in recent years, therefore, it is necessary and worth reviewing the related literature. This study aims to investigate recent advances in the multi-hop MRC approaches based on 31 studies from 2018 to 2022. In this regard, first, the multi-hop MRC problem definition will be introduced, then 31 models will be reviewed in detail with a strong focus on their multi-hop aspects. They also will be categorized based on their main techniques. Finally, a fine-grain comprehensive comparison of the models and techniques will be presented.

As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability, transparency (FaccT), and unbiasedness. Recently, techniques in Explainable Artificial Intelligence (XAI) are attracting considerable attention, and have tremendously helped Machine Learning (ML) engineers in understanding AI models. However, at the same time, we started to witness the emerging need beyond XAI among AI communities; based on the insights learned from XAI, how can we better empower ML engineers in steering their DNNs so that the model's reasonableness and performance can be improved as intended? This article provides a timely and extensive literature overview of the field Explanation-Guided Learning (EGL), a domain of techniques that steer the DNNs' reasoning process by adding regularization, supervision, or intervention on model explanations. In doing so, we first provide a formal definition of EGL and its general learning paradigm. Secondly, an overview of the key factors for EGL evaluation, as well as summarization and categorization of existing evaluation procedures and metrics for EGL are provided. Finally, the current and potential future application areas and directions of EGL are discussed, and an extensive experimental study is presented aiming at providing comprehensive comparative studies among existing EGL models in various popular application domains, such as Computer Vision (CV) and Natural Language Processing (NLP) domains.

Recently, automated co-design of machine learning (ML) models and accelerator architectures has attracted significant attention from both the industry and academia. However, most co-design frameworks either explore a limited search space or employ suboptimal exploration techniques for simultaneous design decision investigations of the ML model and the accelerator. Furthermore, training the ML model and simulating the accelerator performance is computationally expensive. To address these limitations, this work proposes a novel neural architecture and hardware accelerator co-design framework, called CODEBench. It is composed of two new benchmarking sub-frameworks, CNNBench and AccelBench, which explore expanded design spaces of convolutional neural networks (CNNs) and CNN accelerators. CNNBench leverages an advanced search technique, BOSHNAS, to efficiently train a neural heteroscedastic surrogate model to converge to an optimal CNN architecture by employing second-order gradients. AccelBench performs cycle-accurate simulations for a diverse set of accelerator architectures in a vast design space. With the proposed co-design method, called BOSHCODE, our best CNN-accelerator pair achieves 1.4% higher accuracy on the CIFAR-10 dataset compared to the state-of-the-art pair, while enabling 59.1% lower latency and 60.8% lower energy consumption. On the ImageNet dataset, it achieves 3.7% higher Top1 accuracy at 43.8% lower latency and 11.2% lower energy consumption. CODEBench outperforms the state-of-the-art framework, i.e., Auto-NBA, by achieving 1.5% higher accuracy and 34.7x higher throughput, while enabling 11.0x lower energy-delay product (EDP) and 4.0x lower chip area on CIFAR-10.

As an efficient graph analytical tool, graph neural networks (GNNs) have special properties that are particularly fit for the characteristics and requirements of wireless communications, exhibiting good potential for the advancement of next-generation wireless communications. This article aims to provide a comprehensive overview of the interplay between GNNs and wireless communications, including GNNs for wireless communications (GNN4Com) and wireless communications for GNNs (Com4GNN). In particular, we discuss GNN4Com based on how graphical models are constructed and introduce Com4GNN with corresponding incentives. We also highlight potential research directions to promote future research endeavors for GNNs in wireless communications.