In this paper, we propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors and make it easier to simulate output distribution of deep neural network. With these observations, we propose a novel Bayesian adversarial example detector, short for BATer, to improve the performance of adversarial example detection. In specific, we study the distributional difference of hidden layer output between natural and adversarial examples, and propose to use the randomness of Bayesian neural network (BNN) to simulate hidden layer output distribution and leverage the distribution dispersion to detect adversarial examples. The advantage of BNN is that the output is stochastic while neural networks without random components do not have such characteristics. Empirical results on several benchmark datasets against popular attacks show that the proposed BATer outperforms the state-of-the-art detectors in adversarial example detection.
There is still a long way to go before artificial mini robots are really used for search and rescue missions in disaster-hit areas due to hindrance in power consumption, computation load of the locomotion, and obstacle-avoidance system. Insect-computer hybrid system, which is the fusion of living insect platform and microcontroller, emerges as an alternative solution. This study demonstrates the first-ever insect-computer hybrid system conceived for search and rescue missions, which is capable of autonomous navigation and human presence detection in an unstructured environment. Customized navigation control algorithm utilizing the insect's intrinsic navigation capability achieved exploration and negotiation of complex terrains. On-board high-accuracy human presence detection using infrared camera was achieved with a custom machine learning model. Low power consumption suggests system suitability for hour-long operations and its potential for realization in real-life missions.
In this work, we propose an interactive system to design diverse high-quality garment images from fashion sketches and the texture information. The major challenge behind this system is to generate high-quality and detailed texture according to the user-provided texture information. Prior works mainly use the texture patch representation and try to map a small texture patch to a whole garment image, hence unable to generate high-quality details. In contrast, inspired by intrinsic image decomposition, we decompose this task into texture synthesis and shading enhancement. In particular, we propose a novel bi-colored edge texture representation to synthesize textured garment images and a shading enhancer to render shading based on the grayscale edges. The bi-colored edge representation provides simple but effective texture cues and color constraints, so that the details can be better reconstructed. Moreover, with the rendered shading, the synthesized garment image becomes more vivid.
Communication compression has been extensively adopted to speed up large-scale distributed optimization. However, most existing decentralized algorithms with compression are unsatisfactory in terms of convergence rate and stability. In this paper, we delineate two key obstacles in the algorithm design -- data heterogeneity and compression error. Our attempt to explicitly overcome these obstacles leads to a novel decentralized algorithm named LEAD. This algorithm is the first \underline{L}in\underline{EA}r convergent \underline{D}ecentralized algorithm with communication compression. Our theory describes the coupled dynamics of the inaccurate model propagation and optimization process. We also provide the first consensus error bound without assuming bounded gradients. Empirical experiments validate our theoretical analysis and show that the proposed algorithm achieves state-of-the-art computation and communication efficiency.
Naloxone, an opioid antagonist, has been widely used to save lives from opioid overdose, a leading cause for death in the opioid epidemic. However, naloxone has short brain retention ability, which limits its therapeutic efficacy. Developing better opioid antagonists is critical in combating the opioid epidemic.Instead of exhaustively searching in a huge chemical space for better opioid antagonists, we adopt reinforcement learning which allows efficient gradient-based search towards molecules with desired physicochemical and/or biological properties. Specifically, we implement a deep reinforcement learning framework to discover potential lead compounds as better opioid antagonists with enhanced brain retention ability. A customized multi-objective reward function is designed to bias the generation towards molecules with both sufficient opioid antagonistic effect and enhanced brain retention ability. Thorough evaluation demonstrates that with this framework, we are able to identify valid, novel and feasible molecules with multiple desired properties, which has high potential in drug discovery.
This paper presents a new fractional-order normalized Bouc-Wen (BW) (FONBW) model to describe the asymmetric and rate-dependent hysteresis nonlinearity of piezoelectric actuators (PEAs). In view of the fact that the classical BW (CBW) model is only efficient for the symmetric and rate-independent hysteresis description, the FONBW model is devoted to characterizing the asymmetric and rate-dependent behaviors of the hysteresis in PEAs by adopting a generalized input function and two fractional operators, respectively. Different from the traditional modified BW models, the proposed FONBW model also eliminates the redundancy of parameters in the CBW model via the normalization processing. By this way, the developed FONBW model has a relative simple mathematic expression with fewer parameters to simultaneously characterize the asymmetric and rate-dependent hysteresis behaviors of PEAs. Model parameters are identified by the self-adaptive differential evolution algorithm. To validate the effectiveness of the proposed model, a series of experimental studies are carried out on a PEA system. Results show that the proposed model is superior to the CBW model in accuracy.
Large-scale machine learning models are often trained by parallel stochastic gradient descent algorithms. However, the communication cost of gradient aggregation and model synchronization between the master and worker nodes becomes the major obstacle for efficient learning as the number of workers and the dimension of the model increase. In this paper, we propose DORE, a DOuble REsidual compression stochastic gradient descent algorithm, to reduce over $95\%$ of the overall communication such that the obstacle can be immensely mitigated. Our theoretical analyses demonstrate that the proposed strategy has superior convergence properties for both strongly convex and nonconvex objective functions. The experimental results validate that DORE achieves the best communication efficiency while maintaining similar model accuracy and convergence speed in comparison with start-of-the-art baselines.
As a general-purpose generative model architecture, VAE has been widely used in the field of image and natural language processing. VAE maps high dimensional sample data into continuous latent variables with unsupervised learning. Sampling in the latent variable space of the feature, VAE can construct new image or text data. As a general-purpose generation model, the vanilla VAE can not fit well with various data sets and neural networks with different structures. Because of the need to balance the accuracy of reconstruction and the convenience of latent variable sampling in the training process, VAE often has problems known as "posterior collapse". images reconstructed by VAE are also often blurred. In this paper, we analyze the main cause of these problem, which is the lack of mutual information between the sample variable and the latent feature variable during the training process. To maintain mutual information in model training, we propose to use the auxiliary softmax multi-classification network structure to improve the training effect of VAE, named VAE-AS. We use MNIST and Omniglot data sets to test the VAE-AS model. Based on the test results, It can be show that VAE-AS has obvious effects on the mutual information adjusting and solving the posterior collapse problem.