Abstract
Supervised learning techniques construct predictive models by learning from a large number of training examples, where each training example has a label indicating its ground-truth output. ...Though current techniques have achieved great success, it is noteworthy that in many tasks it is difficult to get strong supervision information like fully ground-truth labels due to the high cost of the data-labeling process. Thus, it is desirable for machine-learning techniques to work with weak supervision. This article reviews some research progress of weakly supervised learning, focusing on three typical types of weak supervision: incomplete supervision, where only a subset of training data is given with labels; inexact supervision, where the training data are given with only coarse-grained labels; and inaccurate supervision, where the given labels are not always ground-truth.
The rapid progress of proton exchange membrane fuel cells (PEMFCs) and alkaline exchange membrane fuel cells (AMFCs) has boosted the hydrogen economy concept via diverse energy applications in the ...past decades. For a holistic understanding of the development status of PEMFCs and AMFCs, recent advancements in electrocatalyst design and catalyst layer optimization, along with cell performance in terms of activity and durability in PEMFCs and AMFCs, are summarized here. The activity, stability, and fuel cell performance of different types of electrocatalysts for both oxygen reduction reaction and hydrogen oxidation reaction are discussed and compared. Research directions on the further development of active, stable, and low‐cost electrocatalysts to meet the ultimate commercialization of PEMFCs and AMFCs are also discussed.
The development of fuel cells is of great significance for achieving a sustainable society. Recent progress in cathodic electrocatalysts for proton exchange membrane fuel cells and anodic and cathodic electrocatalysts for alkaline exchange membrane fuel cells is summarized. The rational design strategies, structure evolution, activities, fuel cell performance, and durability of noble‐metal‐ and non‐noble‐metal‐based electrocatalysts are discussed.
A Review on Multi-Label Learning Algorithms Zhang, Min-Ling; Zhou, Zhi-Hua
IEEE transactions on knowledge and data engineering,
08/2014, Volume:
26, Issue:
8
Journal Article
Peer reviewed
Multi-label learning studies the problem where each example is represented by a single instance while associated with a set of labels simultaneously. During the past decade, significant amount of ...progresses have been made toward this emerging machine learning paradigm. This paper aims to provide a timely review on this area with emphasis on state-of-the-art multi-label learning algorithms. Firstly, fundamentals on multi-label learning including formal definition and evaluation metrics are given. Secondly and primarily, eight representative multi-label learning algorithms are scrutinized under common notations with relevant analyses and discussions. Thirdly, several related learning settings are briefly summarized. As a conclusion, online resources and open research problems on multi-label learning are outlined for reference purposes.
Deep forest Zhou, Zhi-Hua; Feng, Ji
National science review,
01/2019, Volume:
6, Issue:
1
Journal Article
Peer reviewed
Open access
Abstract
Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this ...paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines, we conjecture that the success of deep neural networks owes much to three characteristics, i.e. layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand, our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation.
It is well-known that exploiting label correlations is important to multi-label learning. Existing approaches either assume that the label correlations are global and shared by all instances; or that ...the label correlations are local and shared only by a data subset. In fact, in the real-world applications, both cases may occur that some label correlations are globally applicable and some are shared only in a local group of instances. Moreover, it is also a usual case that only partial labels are observed, which makes the exploitation of the label correlations much more difficult. That is, it is hard to estimate the label correlations when many labels are absent. In this paper, we propose a new multi-label approach GLOCAL dealing with both the full-label and the missing-label cases, exploiting global and local label correlations simultaneously, through learning a latent label representation and optimizing label manifolds. The extensive experimental studies validate the effectiveness of our approach on both full-label and missing-label data.
As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run ...computation-intensive DNN-based tasks on mobile devices due to the limited computation resources. What's worse, traditional cloud-assisted DNN inference is heavily hindered by the significant wide-area network latency, leading to poor real-time performance as well as low quality of user experience. To address these challenges, in this paper, we propose Edgent, a framework that leverages edge computing for DNN collaborative inference through device-edge synergy. Edgent exploits two design knobs: (1) DNN partitioning that adaptively partitions computation between device and edge for purpose of coordinating the powerful cloud resource and the proximal edge resource for real-time DNN inference; (2) DNN right-sizing that further reduces computing latency via early exiting inference at an appropriate intermediate DNN layer. In addition, considering the potential network fluctuation in real-world deployment, Edgent is properly design to specialize for both static and dynamic network environment. Specifically, in a static environment where the bandwidth changes slowly, Edgent derives the best configurations with the assist of regression-based prediction models, while in a dynamic environment where the bandwidth varies dramatically, Edgent generates the best execution plan through the online change point detection algorithm that maps the current bandwidth state to the optimal configuration. We implement Edgent prototype based on the Raspberry Pi and the desktop PC and the extensive experimental evaluations demonstrate Edgent's effectiveness in enabling on-demand low-latency edge intelligence.
While recognition of most facial variations, such as identity, expression, and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast to other facial ...variations, aging variation presents several unique characteristics which make age estimation a challenging task. This paper proposes an automatic age estimation method named AGES (AGing pattErn Subspace). The basic idea is to model the aging pattern, which is defined as the sequence of a particular individual's face images sorted in time order, by constructing a representative subspace. The proper aging pattern for a previously unseen face image is determined by the projection in the subspace that can reconstruct the face image with minimum reconstruction error, while the position of the face image in that aging pattern will then indicate its age. In the experiments, AGES and its variants are compared with the limited existing age estimation methods (WAS and AAS) and some well-established classification methods (kNN, BP, C4.5, and SVM). Moreover, a comparison with human perception ability on age is conducted. It is interesting to note that the performance of AGES is not only significantly better than that of all the other algorithms, but also comparable to that of the human observers.
At the end of December 2019, a novel coronavirus, 2019-nCoV, caused an outbreak of pneumonia spreading from Wuhan, Hubei province, to the whole country of China, which has posed great threats to ...public health and attracted enormous attention around the world. To date, there are no clinically approved vaccines or antiviral drugs available for these human coronavirus infections. Intensive research on the novel emerging human infectious coronaviruses is urgently needed to elucidate their route of transmission and pathogenic mechanisms, and to identify potential drug targets, which would promote the development of effective preventive and therapeutic countermeasures. Herein, we describe the epidemic and etiological characteristics of 2019-nCoV, discuss its essential biological features, including tropism and receptor usage, summarize approaches for disease prevention and treatment, and speculate on the transmission route of 2019-nCoV.
One of the main difficulties in facial age estimation is that the learning algorithms cannot expect sufficient and complete training data. Fortunately, the faces at close ages look quite similar ...since aging is a slow and smooth process. Inspired by this observation, instead of considering each face image as an instance with one label (age), this paper regards each face image as an instance associated with a label distribution. The label distribution covers a certain number of class labels, representing the degree that each label describes the instance. Through this way, one face image can contribute to not only the learning of its chronological age, but also the learning of its adjacent ages. Two algorithms, named IIS-LLD and CPNN, are proposed to learn from such label distributions. Experimental results on two aging face databases show remarkable advantages of the proposed label distribution learning algorithms over the compared single-label learning algorithms, either specially designed for age estimation or for general purpose.