Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the...
详细信息
We develop a deep convolutional neural network (DCNN) based framework for model-free prediction of the occurrence of extreme events both in time ("when") and in space ("where") in nonlinear physica...
详细信息
Fault diagnosis is a vital technique to pinpoint the machine malfunctions in manufacturing systems. In recent years, the deep learning techniques greatly improve the fault detection accuracy, but there still remain so...
详细信息
ISBN:
(数字)9781728169040
ISBN:
(纸本)9781728169057
Fault diagnosis is a vital technique to pinpoint the machine malfunctions in manufacturing systems. In recent years, the deep learning techniques greatly improve the fault detection accuracy, but there still remain some problems. If one fault is absent in the training data or the fault signal is disturbed by severe noise interference, the fault classifier may misjudge the health state. This problem limits the reliability of the fault diagnosis in real applications. In this paper, we enhance the fault diagnosis method by using Bayesian Convolutional Neural Network (BCNN). A Shannon entropy-based method is presented to quantify the prediction uncertainty. The BCNN turns the deterministic predictions to probabilistic distributions and enhances the robustness of the fault diagnosis. The uncertainty quantification method helps to indicate the wrong predictions, detect unknown faults, and discover the strong disturbances. Then, a fine-tuning strategy is applied to enhance the model performance further. The potential usability of the proposed method in monitoring the motors of 3D printers is studied. And the experiment is conducted on a motor bearing dataset provided by Case Western Reserve University. The proposed BCNN achieves 99.82% fault classification accuracy over nine health conditions. Its robustness is verified by comparing the testing accuracy with three other methods on the noisy datasets. And the uncertainty quantification method successfully detects the outlier inputs.
The technological breakthrough in Generative Adversarial Networks (GAN) has propelled the advancement of content generative applications such as AI-based paintings, style transfer, and music composition. However, in c...
详细信息
The technological breakthrough in Generative Adversarial Networks (GAN) has propelled the advancement of content generative applications such as AI-based paintings, style transfer, and music composition. However, in contrast to previous deep learning models for prediction and categorization, generative networks generally rely on instance normalization (IN) layer for better feature distribution, which performs significantly better than batch normalization(BN) in image style-transfer, image to image translation, etc. Unlike batch or group normalization that can be fused into convolutional layers and ignored during the network inference stage, an instance normalization layer induces intensive computation and memory access. However, prior deep learning accelerator designs for traditional Neural Network and Generative Adversarial Networks mostly focus on the acceleration of convolution and deconvolution layer but lack of support for IN operations, which could become a performance bottleneck on edge devices with insufficient computational power. To address this problem, we propose an inference accelerator for content generation (ACG-Engine) aimed to support the fundamental operations of generative networks, including convolution layers, deconvolution layers, specifically instance normalization layer. We performed a hardware-aware mathematical transformation of the IN operation for less computation complexity and memory-friendliness, so that it can be efficiently mapped to the classic 2D processing element array. Owing to the proposed optimization techniques, ACG-Engine achieves 4.56X speedup and improve power efficiency up to 29X compared to prior baseline acceleration scheme in generative network acceleration. In addition, ACG-Engine can achieve performance comparable to the classic CNN-specific accelerators with negligible power consumption and area overhead.
Aerial imagery plays an important role in land-use planning, population analysis, precision agriculture, and unmanned aerial vehicle tasks. However, existing aerial image datasets generally suffer from the problem of ...
详细信息
ISBN:
(数字)9781728173955
ISBN:
(纸本)9781728173962
Aerial imagery plays an important role in land-use planning, population analysis, precision agriculture, and unmanned aerial vehicle tasks. However, existing aerial image datasets generally suffer from the problem of inaccurate labeling, single ground truth type, and few category numbers. In this work, we implement a simulator that can simultaneously acquire diverse visual ground truth data in the virtual environment. Based on that, we collect a comprehensive Virtual AeriaL Image Dataset named VALID, consisting of 6690 high-resolution images, all annotated with panoptic segmentation on 30 categories, object detection with oriented bounding box, and binocular depth maps, collected in 6 different virtual scenes and 5 various ambient conditions (sunny, dusk, night, snow and fog). To our knowledge, VALID is the first aerial image dataset that can provide panoptic level segmentation and complete dense depth maps. We analyze the characteristics of VALID and evaluate state-of-the-art methods for multiple tasks to provide reference baselines. The experiment results demonstrate that VALID is well presented and challenging. The dataset is available at https://***/view/valid-dataset/.
Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of er...
详细信息
Infrared small target detection (ISTD) is vital for long-range surveillance systems, particularly in military defense, maritime monitoring, and early warning applications. Despite its strategic importance, ISTD remain...
详细信息
Hierarchical networks are frequently encountered in animal groups, gene networks, and artificial engineering systems such as multiple robots, unmanned vehicle systems, smart grids, wind farm networks,and so forth. The...
Hierarchical networks are frequently encountered in animal groups, gene networks, and artificial engineering systems such as multiple robots, unmanned vehicle systems, smart grids, wind farm networks,and so forth. The structure of a large directed hierarchical network is often strongly influenced by reverse edges from lower-to higher-level nodes, such as lagging birds' howl in a flock or the opinions of lowerlevel individuals feeding back to higher-level ones in a social group. This study reveals that, for most large-scale real hierarchical networks, the majority of the reverse edges do not affect the synchronization process of the entire network; the synchronization process is influenced only by a small part of these reverse edges along specific paths. More surprisingly, a single effective reverse edge can slow down the synchronization of a huge hierarchical network by over 60%. The effect of such edges depends not on the network size but only on the average in-degree of the involved subnetwork. The overwhelming majority of active reverse edges turn out to have some kind of ‘‘bunchingo effect on the information flows of hierarchical networks, which slows down synchronization processes. This finding refines the current understanding of the role of reverse edges in many natural, social, and engineering hierarchical networks,which might be beneficial for precisely tuning the synchronization rhythms of these networks. Our study also proposes an effective way to attack a hierarchical network by adding a malicious reverse edge to it and provides some guidance for protecting a network by screening out the specific small proportion of vulnerable nodes.
Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However...
详细信息
暂无评论