Unsupervised learning with generative adversarial networks (GANs) has proven to be hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss for both the discriminator and the generator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson χ 2 divergence. We also show that the derived objective function that yields minimizing the Pearson χ 2 divergence performs better than the classical one of using least squares for classification. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stably during the learning process. For evaluating the image quality, we conduct both qualitative and quantitative experiments, and the experimental results show that LSGANs can generate higher quality images than regular GANs. Furthermore, we evaluate the stability of LSGANs in two groups. One is to compare between LSGANs and regular GANs without gradient penalty. We conduct three experiments, including Gaussian mixture distribution, difficult architectures, and a newly proposed method -datasets with small variability, to illustrate the stability of LSGANs. The other one is to compare between LSGANs with gradient penalty (LSGANs-GP) and WGANs with gradient penalty (WGANs-GP). The experimental results show that LSGANs-GP succeed in training for all the difficult architectures used in WGANs-GP, including 101-layer ResNet.

Fiber microactuators are interesting in wide variety of emerging fields, including artificial muscles, biosensors, and wearable devices. In the present study, a robust, fast‐responsive, and humidity‐induced silk fiber microactuator is developed by integrating force‐reeling and yarn‐spinning techniques. The shape gradient, together with hierarchical rough surface, allows these silk fiber microactuators to respond rapidly to humidity. The silk fiber microactuator can reach maximum rotation speed of 6179.3° s−1 in 4.8 s. Such a response speed (1030 rotations per minute) is comparable with the most advanced microactuators. Moreover, this microactuator generates 2.1 W kg−1 of average actuation power, which is twice higher than fiber actuators constructed by cocoon silks. The actuating powers of silk fiber microactuators can be precisely programmed by controlling the number of fibers used. Lastly, theory predicts the observed performance merits of silk fiber microactuators toward inspiring the rational design of water‐induced microactuators.

Factorization Machines (FMs) refer to a class of general predictors working with real valued feature vectors, which are well-known for their ability to estimate model parameters under significant sparsity and have found successful applications in many areas such as the click-through rate (CTR) prediction. However, standard FMs only produce a single fixed representation for each feature across different input instances, which may limit the CTR model’s expressive and predictive power. Inspired by the success of Input-aware Factorization Machines (IFMs), which aim to learn more flexible and informative representations of a given feature according to different input instances, we propose a novel model named Dual Input-aware Factorization Machines (DIFMs) that can adaptively reweight the original feature representations at the bit-wise and vector-wise levels simultaneously. Furthermore, DIFMs strategically integrate various components including Multi-Head Self-Attention, Residual Networks and DNNs into a unified end-to-end model. Comprehensive experiments on two real-world CTR prediction datasets show that the DIFM model can outperform several state-of-the-art models consistently.

Factorization machines (FMs) are a class of general predictors working effectively with sparse data, which represents features using factorized parameters and weights. However, the accuracy of FMs can be adversely affected by the fixed representation trained for each feature, as the same feature is usually not equally predictive and useful in different instances. In fact, the inaccurate representation of features may even introduce noise and degrade the overall performance. In this work, we improve FMs by explicitly considering the impact of individual input upon the representation of features. We propose a novel model named \textit{Input-aware Factorization Machine} (IFM), which learns a unique input-aware factor for the same feature in different instances via a neural network. Comprehensive experiments on three real-world recommendation datasets are used to demonstrate the effectiveness and mechanism of IFM. Empirical results indicate that IFM is significantly better than the standard FM model and consistently outperforms four state-of-the-art deep learning based methods.

No abstract

Concrete surface crack detection based on computer vision, specifically via a convolutional neural network, has drawn increasing attention for replacing manual visual inspection of bridges and buildings. This article proposes a new framework for this task and a sampling and training method based on active learning to treat class imbalances. In particular, the new framework includes a clear definition of two categories of samples, a relevant sliding window technique, data augmentation and annotation methods. The advantages of this framework are that data integrity can be ensured and a very large amount of annotation work can be saved. Training datasets generated with the proposed sampling and training method not only are representative of the original dataset but also highlight samples that are highly complex, yet informative. Based on the proposed framework and sampling and training strategy, AlexNet is re-tuned, validated, tested and compared with an existing network. The investigation revealed outstanding performances of the proposed framework in terms of the detection accuracy, precision and F1 measure due to its nonlinear learning ability, training dataset integrity and active learning strategy.

The subject of this paper is the design and analysis of a biped line walking robot for inspection of power transmission lines. With a novel mechanism the centroid of the robot can be concentrated on the axis of hip joint to minimize the drive torque of the hip joint. The mechanical structure of the robot is discussed, as well as forward kinematics. Dynamic model is established in this paper to analyze the inverse kinematics for motion planning. The line-walking cycle of the line-walking robot is composed of a single-support phase and a double-support phase. Locomotion of the line-walking robot is discussed in details and the obstacle-navigation process is planed according to the structure of power transmission line. To fulfill the demands of line-walking, a control system and trajectories generation method are designed for the prototype of the line-walking robot. The feasibility of this concept is then confirmed by performing experiments with a simulated line environment.

No abstract