Wuhan University

About: Wuhan University is a education organization based out in Wuhan, China. It is known for research contribution in the topics: Computer science & Population. The organization has 92849 authors who have published 92882 publications receiving 1691049 citations. The organization is also known as: WHU & Wuhan College.

Adversarial Attacks on Deep-learning Models in Natural Language Processing: A Survey

Abstract: With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs are vulnerable to strategically modified samples, named adversarial examples. These samples are generated with some imperceptible perturbations, but can fool the DNNs to give false predictions. Inspired by the popularity of generating adversarial examples against DNNs in Computer Vision (CV), research efforts on attacking DNNs for Natural Language Processing (NLP) applications have emerged in recent years. However, the intrinsic difference between image (CV) and text (NLP) renders challenges to directly apply attacking methods in CV to NLP. Various methods are proposed addressing this difference and attack a wide range of NLP applications. In this article, we present a systematic survey on these works. We collect all related academic works since the first appearance in 2017. We then select, summarize, discuss, and analyze 40 representative works in a comprehensive way. To make the article self-contained, we cover preliminary knowledge of NLP and discuss related seminal works in computer vision. We conclude our survey with a discussion on open issues to bridge the gap between the existing progress and more robust adversarial attacks on NLP DNNs.

Online portfolio selection: A survey

Abstract: Online portfolio selection is a fundamental problem in computational finance, which has been extensively studied across several research communities, including finance, statistics, artificial intelligence, machine learning, and data mining. This article aims to provide a comprehensive survey and a structural understanding of online portfolio selection techniques published in the literature. From an online machine learning perspective, we first formulate online portfolio selection as a sequential decision problem, and then we survey a variety of state-of-the-art approaches, which are grouped into several major categories, including benchmarks, Follow-the-Winner approaches, Follow-the-Loser approaches, Pattern-Matching--based approaches, and Meta-Learning Algorithms. In addition to the problem formulation and related algorithms, we also discuss the relationship of these algorithms with the capital growth theory so as to better understand the similarities and differences of their underlying trading ideas. This article aims to provide a timely and comprehensive survey for both machine learning and data mining researchers in academia and quantitative portfolio managers in the financial industry to help them understand the state of the art and facilitate their research and practical applications. We also discuss some open issues and evaluate some emerging new trends for future research.

Green Fabrication of Amphiphilic Quaternized β-Chitin Derivatives with Excellent Biocompatibility and Antibacterial Activities for Wound Healing.

Abstract: Bacterial infection has always been a great threat to public health, and new antimicrobials to combat it are urgently needed. Here, a series of quaternized β-chitin derivatives is prepared simply and homogeneously in an aqueous KOH/urea solution, which is a high-efficiency, energy-saving, and "green" route for the modification of chitin. The mild reaction conditions keep the acetamido groups of β-chitin intact and introduce quaternary ammonium groups on the primary hydroxyl at the C-6 position of the chitin backbone, allowing the quaternized β-chitin derivatives (QCs) to easily form micelles. These QCs are found to exhibit excellent antimicrobial activities against Escherichia coli, Staphylococcus aureus, Candida albicans, and Rhizopus oryzae with minimum inhibitory concentrations (MICs) of 8, 12, 60, and 40 µg mL-1 , respectively. As a specific highlight, their inherent outstanding biocompatibility and significant accelerating effects on the healing of uninfected, E. coli-infected, and S. aureus-infected wounds imply that these novel polysaccharide-based materials can be used as dressings for clinical skin regeneration, particularly for infected wounds.