3,800 Hits in 6.1 sec

Mesh-Based Affine Abstraction of Nonlinear Systems with Tighter Bounds [article]

Kanishka Raj Singh and Qiang Shen and Sze Zheng Yong
2018 arXiv   pre-print
As such, guarantees for controllers or estimators based on the affine abstraction also apply to the original nonlinear system.  ...  In this paper, we consider the problem of piecewise affine abstraction of nonlinear systems, i.e., the overapproximation of its nonlinear dynamics by a pair of piecewise affine functions that "includes  ...  The authors are with School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, USA (email: {kanishka.r.singh,qiang.shen,szyong} This work was supported in part by  ... 
arXiv:1811.02482v1 fatcat:bqfgbtfr2jgkhcwfswlnq7xrqi

Sequence2Vec: a novel embedding approach for modeling transcription factor binding affinity landscape

Hanjun Dai, Ramzan Umarov, Hiroyuki Kuwahara, Yu Li, Le Song, Xin Gao, Oliver Stegle
2017 Bioinformatics  
Results: Here we propose a novel sequence embedding approach for modeling the transcription factor binding affinity landscape.  ...  While recent advances in biotechnology have brought the opportunity for building binding affinity prediction methods, the accurate characterization of TF-DNA binding affinity landscape still remains a  ...  That is, our method can handle inputs of different lengths. End-to-end discriminative training In previous sections, we assumed that the parameters in the nonlinear feature embeddings are given.  ... 
doi:10.1093/bioinformatics/btx480 pmid:28961686 pmcid:PMC5870668 fatcat:upgk3pfk7fa4vgymswouqbxh7i

Deep understanding of big multimedia data

Xiaofeng Zhu, Chong-Yaw Wee, Minjeong Kim
2020 Neural computing & applications (Print)  
the unsupervised probabilistic generative model for cross-domain abstractive review summarization.  ...  In [9], Li et al. propose an unsupervised nonlinear feature selection method via kernel function.  ...  the unsupervised probabilistic generative model for cross-domain abstractive review summarization.  ... 
doi:10.1007/s00521-020-04885-9 fatcat:wiqlyp5kebdotkti7ljt3cr66m

A Probabilistic Theory of Deep Learning [article]

Ankit B. Patel, Tan Nguyen, Richard G. Baraniuk
2015 arXiv   pre-print
We answer this question by developing a new probabilistic framework for deep learning based on the Deep Rendering Model: a generative probabilistic model that explicitly captures latent nuisance variation  ...  By relaxing the generative model to a discriminative one, we can recover two of the current leading deep learning systems, deep convolutional neural networks and random decision forests, providing insights  ...  Thanks to Ruchi Kukreja for her unwavering support and her humor and to Raina Patel for providing inspiration.  ... 
arXiv:1504.00641v1 fatcat:dsqdeopvrjdhrhrd6ytmsjhyzq

State and Unknown Terrain Estimation for Planetary Rovers via Interval Observers

Mohammad Khajenejad, Zeyuan Jin, Sze Zheng Yong
2021 Advanced Intelligent Systems  
By leveraging a combination of nonlinear bounding/decomposition functions, affine abstractions, and a data-driven function abstraction method (to overestimate the unknown dynamics model from noisy input-output  ...  For this purpose, a state and model interval observer is designed for partially unknown nonlinear systems with bounded noise.  ...  Appendix Observer Gain Definitions ∀J ∈ fA, Wg, q ∈ ff , ϕg, J ∈ fA, Wg, i ∈ f1 : : : ∞g In addition, ðA q k , B q k , W q k , e q k , e q k Þ for q ∈ ff , ϕg and ðA  ... 
doi:10.1002/aisy.202100040 fatcat:bat4ls2viffa3f2ymxwqkeqdli

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., Reference Trajectory Reshaping Optimi-zation and Control of Robotic Exoskeletons for Human-Robot Co-Manipulation; TCYB Aug. 2020 3740-3751 Wu, X., Jiang, B., Yu, K., Miao, c., and Chen, H  ...  ., +, TCYB May 2020 2264-2273 A Novel Piecewise Affine Filtering Design for T-S Fuzzy Affine Systems Using Past Output Measurements.  ...  ., +, TCYB Jan. 2020 112-125 A Novel Piecewise Affine Filtering Design for T-S Fuzzy Affine Systems Using Past Output Measurements.  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

Image Synthesis via Semantic Composition [article]

Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia
2021 arXiv   pre-print
It hypothesizes that for objects with similar appearance, they share similar representation.  ...  The corresponding optimization goal for the discriminator is For the discriminator, we directly employ the feature pyramid semantics-embedding discriminator from [21] .  ...  . • We propose a new generator design for GAN-based semantic image synthesis.  ... 
arXiv:2109.07053v1 fatcat:tvs264q3djcsjnr4chmz3ralra

SymReg-GAN: Symmetric Image Registration with Generative Adversarial Networks

Yuanjie Zheng, Xiaodan Sui, Yanyun Jiang, Tontong Che, Shaoting Zhang, Jie Yang, Hongsheng Li
2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
or high labor cost for labeling data.  ...  The registration symmetry is realized by introducing a loss for encouraging that the cycle composed of the geometric transformation from one image to another and its reverse should bring an image back.  ...  ACKNOWLEDGMENTS We thank all the editors and reviewers for their insightful suggestions.  ... 
doi:10.1109/tpami.2021.3083543 pmid:34033536 fatcat:ggeds7ldhjb37nhqavcvfuwd2a

A nonlinear extension of the MACE filter

John W. Fisher, Jose C. Principe
1995 Neural Networks  
A method by which nonlinear topologies can be incorporated into the filter design is presented and adaptation issues are discussed.  ...  A method by which nonlinear topologies can be incorporated into the filter design is presented and adaptation issues are discussed.  ...  improved performance via a nonlinear discriminant function.  ... 
doi:10.1016/0893-6080(95)00060-7 fatcat:wofc2fx5nna77jq5sovbhnhm5u

Network In Network [article]

Min Lin, Qiang Chen, Shuicheng Yan
2014 arXiv   pre-print
We propose a novel deep network structure called "Network In Network" (NIN) to enhance model discriminability for local patches within the receptive field.  ...  The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input.  ...  This new structure consists of mlpconv layers which use multilayer perceptrons to convolve the input and a global average pooling layer as a replacement for the fully connected layers in conventional CNN  ... 
arXiv:1312.4400v3 fatcat:bicbw4jwqnaazcszad2pev2dpa

PA3D: Pose-Action 3D Machine for Video Recognition

An Yan, Yali Wang, Zhifeng Li, Yu Qiao
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
However, most 3D models are built upon RGB and optical flow streams, which may not fully exploit pose dynamics, i.e., an important cue of modeling human actions.  ...  Recent studies have witnessed the successes of using 3D CNNs for video action recognition.  ...  Multi-Scale Design via Temporal Dilation. For each joint, semantic convolution is performed over all the frames.  ... 
doi:10.1109/cvpr.2019.00811 dblp:conf/cvpr/YanWLQ19 fatcat:hjoteum4knfijg33lqgkj34p6a

EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical Report) [article]

Yujie Ji, Xinyang Zhang, Ting Wang
2018 arXiv   pre-print
By leveraging such properties in a principled manner, EagleEye effectively discriminates adversarial inputs and even uncovers their correct classification outputs.  ...  Our design exploits the minimality principle underlying many attacks: to maximize the attack's evasiveness, the adversary often seeks the minimum possible distortion to convert genuine inputs to adversarial  ...  Addressing the vulnerabilities of deep learning systems to adversarial inputs is more challenging for they are designed to model highly nonlinear, nonconvex functions [31, 36] .  ... 
arXiv:1808.00123v1 fatcat:2ewvoa5yrjbczohmrqquitogfe

Representation Learning with Smooth Autoencoder [chapter]

Kongming Liang, Hong Chang, Zhen Cui, Shiguang Shan, Xilin Chen
2015 Lecture Notes in Computer Science  
In this way, the learned representations are consistent among local neighbors and robust to small variations of the inputs.  ...  In this paper, we propose a novel autoencoder variant, smooth autoencoder (SmAE), to learn robust and discriminative feature representations.  ...  Recent works incorporate manifold regularization into deep learning models and obtain parametric feedforward encoders on nonlinear manifolds, e.g., deep learning via semi-supervised embedding [16] and  ... 
doi:10.1007/978-3-319-16808-1_6 fatcat:ca5ydjwn4bfiznx6anghvr62qi

Correct-By-Construction Exploration and Exploitation for Unknown Linear Systems Using Bilinear Optimization

Kwesi Rutledge, Necmiye Ozay
2022 25th ACM International Conference on Hybrid Systems: Computation and Control  
This set can contain models for different failure or operational modes or potential environmental conditions.  ...  Our approach provides a family of controllers that enable adaptation based on data observed at run-time to automatically trade off model detection and reachability objectives while maintaining safety.  ...  The authors also thank the anonymous reviewers for valuable feedback.  ... 
doi:10.1145/3501710.3519536 fatcat:vavkq3ied5gjndqngapuyvfury

RSMT: A Remote Sensing Image-to-Map Translation Model via Adversarial Deep Transfer Learning

Jieqiong Song, Jun Li, Hao Chen, Jiangjiang Wu
2022 Remote Sensing  
novel attention-based network designs.  ...  In this work, we intend to seek a remote sensing image-to-map translation model that approaches the challenge of generating maps for the remote sensing images of unseen areas.  ...  Overall Architecture We design our model combined with a generator G and a spatial attention-guided discriminator D.  ... 
doi:10.3390/rs14040919 fatcat:ik7oiue2zbcl3p2wjsapbpuubm
« Previous Showing results 1 — 15 out of 3,800 results