搜索结果: 1-11 共查到“人工智能 via”相关记录11条 . 查询时间(0.203 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Graph Refinement via Simultaneously Low-rank and Sparse Approximation
低秩 稀疏近似 图细化
2023/4/18
Graphs play an important role in many fields of machine learning such as clustering. Many graph-based machine learning approaches assume that the graphs have hidden group structures. However, the grou...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Bayesian Approach to Determining the Orientation of Sound-soft Obstacles with Phaseless Data via Wasserstein Distance
Wasserstein距离 贝叶斯方法 无相数据 软声障碍物
2023/4/27
We present a Bayesian approach to inverse scattering problems of reconstructing the rotation angle in clockwise direction of an acoustically sound-soft obstacle from phaseless far-field data in two di...
ACCURACY ESTIMATION OF THE OPTICAL FLOWMETHODS IN THE IRIS STRUCTURE MOTION ANALYSIS VIA CONTROLLED DEFORMATIONS
Biometrics Iris Structure Computer Vision Image Analysis Optical Flow Horn-Schunck Method Lucas-Kanade Method Accuracy Estimation
2017/6/19
The iris structure motion is analyzed. Extension and compression of the iris structural elements are nonlinear with respect to the pupil radius change. To reveal this nonlinearity the Lucas-Kanade, Ho...
Dynamic network energy management via proximal message passing
Network equipment network target device circuit power
2015/8/7
We consider a network of devices, such as generators, fixed loads, deferrable loads, and storage devices, each with its own dynamic constraints and objective, connected by AC and DC lines. The problem...
Security constrained optimal power flow via proximal message passing
Trend network equipment dynamic constraints reliability constraint fault network
2015/8/7
In this paper, we propose a distributed algorithm to solve the Security Constrained Optimal Power Flow (SC-OPF) Problem. We consider a network of devices, each with its own dynamic constraints and obj...
Binding tactile and visual sensations via unique association by cross-anchoring between double-touching and self-occlusion
multimodal binding self-body observation double-touching self-occlusion cross-anchoring Hebbian learning
2015/7/30
Binding is one of the most fundamental cognitive functions, how to find the correspondence of sensations between different modalities such as vision and touch. Without a priori knowledge on this corre...
Consciousness in mixed systems: merging artificial and biological minds via Brain-Machine Interface
consciousness brain-machine interface mind brain implant neuroprotheses neurotechnology
2015/7/15
The rapidly developing field of Brain-Machine Interface (BMI) technology seeks to establish a direct communication-and-control channel between human brain and machines. Practical applications for BMI ...
Speech Feature Denoising and Dereverberation via Deep Autoencoders for Noisy Reverberant Speech Recognition
robust speech recognition feature denoising denoising autoencoder deep neural network
2014/11/27
Denoising autoencoders (DAs) have shown success in generating robust features for images, but there has been limited work in applying DAs for speech. In this paper we present a deep denoising autoenco...
Mispronunciation Detection via Dynamic Time Warping on Deep Belief Network-Based Posteriorgrams
mispronunciation detection dynamic time warping deep belief networks
2014/11/27
In this paper, we explore the use of deep belief network (DBN) posteriorgrams as input to our previously proposed comparison-based system for detecting word-level mispronunciation. The system works by...
A Multimodal Home Entertainment Interface via a Mobile Device
Multimodal Home Entertainment Interface a Mobile Device
2014/11/27
We describe a multimodal dialogue system for interacting with a home entertainment center via a mobile device. In our working prototype, users may utilize both a graphical and speech user interface to...
Reducing Annotation Effort for Quality Estimation via Active Learning
Reducing Annotation Effort Quality Estimation via Active Learning
2014/3/20
Quality estimation models provide feedback on the quality of machine translated texts. They are usually trained on humanannotated datasets, which are very costly due to its task-specific nature. We in...
