Sorry, you need to enable JavaScript to visit this website.

Neural network learning (MLR-NNLR)

CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER

Paper Details

Authors:
Felix Wiewel, Bin Yang
Submitted On:
8 May 2019 - 3:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER

(19)

Subscribe

[1] Felix Wiewel, Bin Yang, "CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4032. Accessed: Jul. 23, 2019.
@article{4032-19,
url = {http://sigport.org/4032},
author = {Felix Wiewel; Bin Yang },
publisher = {IEEE SigPort},
title = {CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER},
year = {2019} }
TY - EJOUR
T1 - CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER
AU - Felix Wiewel; Bin Yang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4032
ER -
Felix Wiewel, Bin Yang. (2019). CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER. IEEE SigPort. http://sigport.org/4032
Felix Wiewel, Bin Yang, 2019. CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER. Available at: http://sigport.org/4032.
Felix Wiewel, Bin Yang. (2019). "CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER." Web.
1. Felix Wiewel, Bin Yang. CONTINUAL LEARNING FOR ANOMALY DETECTION WITH VARIATIONAL AUTOENCODER [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4032

NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster

Paper Details

Authors:
Submitted On:
8 May 2019 - 12:02am
Short Link:
Type:
Event:
Paper Code:

Document Files

NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_Zhixiang Wang

(14)

Subscribe

[1] , "NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4005. Accessed: Jul. 23, 2019.
@article{4005-19,
url = {http://sigport.org/4005},
author = { },
publisher = {IEEE SigPort},
title = {NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster},
year = {2019} }
TY - EJOUR
T1 - NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4005
ER -
. (2019). NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster. IEEE SigPort. http://sigport.org/4005
, 2019. NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster. Available at: http://sigport.org/4005.
. (2019). "NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster." Web.
1. . NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4005

NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster

Paper Details

Authors:
Submitted On:
8 May 2019 - 12:02am
Short Link:
Type:
Event:
Paper Code:

Document Files

NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_Zhixiang Wang

(14)

Subscribe

[1] , "NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4004. Accessed: Jul. 23, 2019.
@article{4004-19,
url = {http://sigport.org/4004},
author = { },
publisher = {IEEE SigPort},
title = {NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster},
year = {2019} }
TY - EJOUR
T1 - NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4004
ER -
. (2019). NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster. IEEE SigPort. http://sigport.org/4004
, 2019. NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster. Available at: http://sigport.org/4004.
. (2019). "NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster." Web.
1. . NON-LOCAL SELF-ATTENTION STRUCTURE FOR FUNCTION APPROXIMATION IN DEEP REINFORCEMENT LEARNING_poster [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4004

SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING


In this paper we propose speaker characterization using time delay neural networks and long short-term memory neural networks (TDNN-LSTM) speaker embedding. Three types of front-end feature extraction are investigated to find good features for speaker embedding. Three kinds of data augmentation are used to increase the amount and diversity of the training data. The proposed methods are evaluated with the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) tasks.

Paper Details

Authors:
Chia-Ping Chen, Su-Yu Zhang, Chih-Ting Yeh, Jia-Ching Wang, Tenghui Wang, Chien-Lin Huang
Submitted On:
7 May 2019 - 11:01pm
Short Link:
Type:
Event:

Document Files

ICASSP2019_poster_A0.pdf

(18)

Subscribe

[1] Chia-Ping Chen, Su-Yu Zhang, Chih-Ting Yeh, Jia-Ching Wang, Tenghui Wang, Chien-Lin Huang, "SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3997. Accessed: Jul. 23, 2019.
@article{3997-19,
url = {http://sigport.org/3997},
author = {Chia-Ping Chen; Su-Yu Zhang; Chih-Ting Yeh; Jia-Ching Wang; Tenghui Wang; Chien-Lin Huang },
publisher = {IEEE SigPort},
title = {SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING},
year = {2019} }
TY - EJOUR
T1 - SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING
AU - Chia-Ping Chen; Su-Yu Zhang; Chih-Ting Yeh; Jia-Ching Wang; Tenghui Wang; Chien-Lin Huang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3997
ER -
Chia-Ping Chen, Su-Yu Zhang, Chih-Ting Yeh, Jia-Ching Wang, Tenghui Wang, Chien-Lin Huang. (2019). SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING. IEEE SigPort. http://sigport.org/3997
Chia-Ping Chen, Su-Yu Zhang, Chih-Ting Yeh, Jia-Ching Wang, Tenghui Wang, Chien-Lin Huang, 2019. SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING. Available at: http://sigport.org/3997.
Chia-Ping Chen, Su-Yu Zhang, Chih-Ting Yeh, Jia-Ching Wang, Tenghui Wang, Chien-Lin Huang. (2019). "SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING." Web.
1. Chia-Ping Chen, Su-Yu Zhang, Chih-Ting Yeh, Jia-Ching Wang, Tenghui Wang, Chien-Lin Huang. SPEAKER CHARACTERIZATION USING TDNN-LSTM BASED SPEAKER EMBEDDING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3997

Learning to Fuse Latent Representations for Multimodal Data

Paper Details

Authors:
Oyebade Oyedotun, Djamila Aouada, Bjorn Ottersten
Submitted On:
7 May 2019 - 5:21pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2019 SnT Poster Template_V07.pdf

(15)

Subscribe

[1] Oyebade Oyedotun, Djamila Aouada, Bjorn Ottersten, "Learning to Fuse Latent Representations for Multimodal Data", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3958. Accessed: Jul. 23, 2019.
@article{3958-19,
url = {http://sigport.org/3958},
author = {Oyebade Oyedotun; Djamila Aouada; Bjorn Ottersten },
publisher = {IEEE SigPort},
title = {Learning to Fuse Latent Representations for Multimodal Data},
year = {2019} }
TY - EJOUR
T1 - Learning to Fuse Latent Representations for Multimodal Data
AU - Oyebade Oyedotun; Djamila Aouada; Bjorn Ottersten
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3958
ER -
Oyebade Oyedotun, Djamila Aouada, Bjorn Ottersten. (2019). Learning to Fuse Latent Representations for Multimodal Data. IEEE SigPort. http://sigport.org/3958
Oyebade Oyedotun, Djamila Aouada, Bjorn Ottersten, 2019. Learning to Fuse Latent Representations for Multimodal Data. Available at: http://sigport.org/3958.
Oyebade Oyedotun, Djamila Aouada, Bjorn Ottersten. (2019). "Learning to Fuse Latent Representations for Multimodal Data." Web.
1. Oyebade Oyedotun, Djamila Aouada, Bjorn Ottersten. Learning to Fuse Latent Representations for Multimodal Data [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3958

OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA


360 camera has recently become popular since it can capture the whole 360 scene. A large number of related applications have been springing up. In this paper, We propose a deep learning based object detector that can be applied directly on 360 images. The proposed detector is based on modifications of the faster RCNN model. Three modification schemes are proposed here, including (1) distortion data augmentation, (2) introducing muilti-kernel layers for improving accuracy for distorted object detection, and (3) adding position information into the model for learning spatial information.

Paper Details

Authors:
Kuan-Hsun Wang, Shang-Hong Lai
Submitted On:
6 May 2019 - 2:43am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster

(18)

Subscribe

[1] Kuan-Hsun Wang, Shang-Hong Lai, "OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3909. Accessed: Jul. 23, 2019.
@article{3909-19,
url = {http://sigport.org/3909},
author = {Kuan-Hsun Wang; Shang-Hong Lai },
publisher = {IEEE SigPort},
title = {OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA},
year = {2019} }
TY - EJOUR
T1 - OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA
AU - Kuan-Hsun Wang; Shang-Hong Lai
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3909
ER -
Kuan-Hsun Wang, Shang-Hong Lai. (2019). OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA. IEEE SigPort. http://sigport.org/3909
Kuan-Hsun Wang, Shang-Hong Lai, 2019. OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA. Available at: http://sigport.org/3909.
Kuan-Hsun Wang, Shang-Hong Lai. (2019). "OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA." Web.
1. Kuan-Hsun Wang, Shang-Hong Lai. OBJECT DETECTION IN CURVED SPACE FOR 360-DEGREE CAMERA [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3909

NEURAL LATTICE DECODERS


Lattice decoders constructed with neural networks are presented.
Firstly, we show how the fundamental parallelotope
is used as a compact set for the approximation by a neural lattice
decoder. Secondly, we introduce the notion of Voronoi reduced
lattice basis. As a consequence, a first optimal neural
lattice decoder is built from Boolean equations and the facets
of the Voronoi cell. This decoder needs no learning. Finally,
we present two neural decoders with learning. It is shown

Paper Details

Authors:
Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, and Loïc Brunel
Submitted On:
23 November 2018 - 10:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

talk_globalSIP.pdf

(51)

Subscribe

[1] Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, and Loïc Brunel, "NEURAL LATTICE DECODERS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3743. Accessed: Jul. 23, 2019.
@article{3743-18,
url = {http://sigport.org/3743},
author = {Vincent Corlay; Joseph J. Boutros; Philippe Ciblat; and Loïc Brunel },
publisher = {IEEE SigPort},
title = {NEURAL LATTICE DECODERS},
year = {2018} }
TY - EJOUR
T1 - NEURAL LATTICE DECODERS
AU - Vincent Corlay; Joseph J. Boutros; Philippe Ciblat; and Loïc Brunel
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3743
ER -
Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, and Loïc Brunel. (2018). NEURAL LATTICE DECODERS. IEEE SigPort. http://sigport.org/3743
Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, and Loïc Brunel, 2018. NEURAL LATTICE DECODERS. Available at: http://sigport.org/3743.
Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, and Loïc Brunel. (2018). "NEURAL LATTICE DECODERS." Web.
1. Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, and Loïc Brunel. NEURAL LATTICE DECODERS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3743

FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS


Here, a novel approach is proposed to generate age progression (i.e., future looks) and regression (i.e., previous looks) of persons based on their face images. The proposed method addresses face aging as an unsupervised image-to-image translation problem where the goal is to translate a face image belonging to an age class to an image of

Paper Details

Authors:
Evangelia Pantraki, Constantine Kotropoulos
Submitted On:
28 November 2018 - 10:52pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

FaceAgingAsIm2ImTranslationUsingShared-LatentSpaceGANs.pdf

(67)

Subscribe

[1] Evangelia Pantraki, Constantine Kotropoulos, "FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3699. Accessed: Jul. 23, 2019.
@article{3699-18,
url = {http://sigport.org/3699},
author = {Evangelia Pantraki; Constantine Kotropoulos },
publisher = {IEEE SigPort},
title = {FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS},
year = {2018} }
TY - EJOUR
T1 - FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS
AU - Evangelia Pantraki; Constantine Kotropoulos
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3699
ER -
Evangelia Pantraki, Constantine Kotropoulos. (2018). FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS. IEEE SigPort. http://sigport.org/3699
Evangelia Pantraki, Constantine Kotropoulos, 2018. FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS. Available at: http://sigport.org/3699.
Evangelia Pantraki, Constantine Kotropoulos. (2018). "FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS." Web.
1. Evangelia Pantraki, Constantine Kotropoulos. FACE AGING AS IMAGE-TO-IMAGE TRANSLATION USING SHARED-LATENT SPACE GENERATIVE ADVERSARIAL NETWORKS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3699

A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture

Paper Details

Authors:
Mohamad Shahbazi, Hamid K. Aghajan
Submitted On:
20 November 2018 - 11:16am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Presentation Slides

(79)

Subscribe

[1] Mohamad Shahbazi, Hamid K. Aghajan, "A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3678. Accessed: Jul. 23, 2019.
@article{3678-18,
url = {http://sigport.org/3678},
author = {Mohamad Shahbazi; Hamid K. Aghajan },
publisher = {IEEE SigPort},
title = {A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture},
year = {2018} }
TY - EJOUR
T1 - A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture
AU - Mohamad Shahbazi; Hamid K. Aghajan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3678
ER -
Mohamad Shahbazi, Hamid K. Aghajan. (2018). A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture. IEEE SigPort. http://sigport.org/3678
Mohamad Shahbazi, Hamid K. Aghajan, 2018. A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture. Available at: http://sigport.org/3678.
Mohamad Shahbazi, Hamid K. Aghajan. (2018). "A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture." Web.
1. Mohamad Shahbazi, Hamid K. Aghajan. A Generalizable Model for Seizure Prediction based on Deep Learning using CNN-LSTM Architecture [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3678

Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications


Network traffic classification, working by associating traffic flows with specific categories or intruders, plays an important role in network management and security. For network traffic classification in wireless communications, the major challenge is encrypted data. Researchers are usually not authorized to get inner information of the traffic flows, and have to analyze traffic features. Machine learning algorithms are widely used as classifiers, and represent learning makes feature extraction more accurate by avoiding manual operation.

Paper Details

Authors:
Jing Ran,Yexin Chen,Shulan Li
Submitted On:
18 November 2018 - 2:48pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Ran-ppt.pdf

(67)

Subscribe

[1] Jing Ran,Yexin Chen,Shulan Li, "Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3675. Accessed: Jul. 23, 2019.
@article{3675-18,
url = {http://sigport.org/3675},
author = {Jing Ran;Yexin Chen;Shulan Li },
publisher = {IEEE SigPort},
title = {Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications},
year = {2018} }
TY - EJOUR
T1 - Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications
AU - Jing Ran;Yexin Chen;Shulan Li
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3675
ER -
Jing Ran,Yexin Chen,Shulan Li. (2018). Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications. IEEE SigPort. http://sigport.org/3675
Jing Ran,Yexin Chen,Shulan Li, 2018. Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications. Available at: http://sigport.org/3675.
Jing Ran,Yexin Chen,Shulan Li. (2018). "Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications." Web.
1. Jing Ran,Yexin Chen,Shulan Li. Three-dimentional Convolution Neural Network based Encrypted Traffic Classifier for Wireless Communications [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3675

Pages