Spatial-Temporal Dynamic Network (STDN) - Revision history

BPeat at 21:45, 28 July 2019

2019-07-28T21:45:14Z

BPeat at 15:27, 28 July 2019

2019-07-28T15:27:22Z

BPeat at 14:37, 28 July 2019

2019-07-28T14:37:01Z

BPeat at 15:39, 27 July 2019

2019-07-27T15:39:02Z

BPeat at 15:23, 27 July 2019

2019-07-27T15:23:03Z

BPeat at 13:01, 27 July 2019

2019-07-27T13:01:09Z

BPeat at 14:54, 3 February 2019

2019-02-03T14:54:10Z

BPeat at 16:52, 13 January 2019

2019-01-13T16:52:05Z

BPeat at 16:50, 13 January 2019

2019-01-13T16:50:26Z

BPeat at 16:48, 13 January 2019

2019-01-13T16:48:14Z

@@ Line 11: / Line 11: @@
 * [[Memory Networks]]
 * [[3D Model]]
-* [[Screening; Passenger & Luggage]]
+* [[Screening; Passenger, Luggage, & Cargo]]
 Recently, with the advances of deep learning techniques, deep leaning models such as [[(Deep) Convolutional Neural Network (DCNN/CNN)]] and [[Recurrent Neural Network (RNN)]]  have enjoyed considerable success in various machine learning tasks due to their powerful hierarchical feature learning ability in both spatial and temporal domains, and have been widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, representation

← Older revision		Revision as of 15:27, 28 July 2019
Line 25:		Line 25:
	<youtube>ROrCPNigCZE</youtube>		<youtube>ROrCPNigCZE</youtube>
	<youtube>hK0mr0BrBAw</youtube>		<youtube>hK0mr0BrBAw</youtube>
−	~~<youtube>v_W3aIPy-Xs</youtube>~~

@@ Line 11: / Line 11: @@
 * [[Memory Networks]]
 * [[3D Model]]
-* [[Passenger Screening]] Challenge
+* [[Screening; Passenger & Luggage]]
 Recently, with the advances of deep learning techniques, deep leaning models such as [[(Deep) Convolutional Neural Network (DCNN/CNN)]] and [[Recurrent Neural Network (RNN)]]  have enjoyed considerable success in various machine learning tasks due to their powerful hierarchical feature learning ability in both spatial and temporal domains, and have been widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, representation

@@ Line 13: / Line 13: @@
 * [[Passenger Screening]] Challenge
-Recently, with the advances of deep learning techniques, deep leaning models such as convolutional neural network (CNN) and recurrent neural network (RNN) have enjoyed considerable success in various machine learning tasks due to their powerful hierarchical feature learning ability in both spatial and temporal domains, and have been widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, representation
+Recently, with the advances of deep learning techniques, deep leaning models such as [[(Deep) Convolutional Neural Network (DCNN/CNN)]] and [[Recurrent Neural Network (RNN)]]  have enjoyed considerable success in various machine learning tasks due to their powerful hierarchical feature learning ability in both spatial and temporal domains, and have been widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, representation
 learning, anomaly detection and classification. [http://arxiv.org/pdf/1906.04928.pdf Deep Learning for Spatio-Temporal Data Mining: A Survey | S. Wang, J. Cao and P. Yu]

@@ Line 12: / Line 12: @@
 * [[3D Model]]
 * [[Passenger Screening]] Challenge
 The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice, the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. [http://arxiv.org/abs/1803.01254 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction | H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li]

← Older revision		Revision as of 14:54, 3 February 2019
Line 1:		Line 1:
		+	{{#seo:
		+	\|title=PRIMO.ai
		+	\|titlemode=append
		+	\|keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS
		+	\|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
		+	}}
	[http://www.youtube.com/results?search_query=Spatialtemporal+Spatial+Temporal+Spatio+Dynamic+Network+STDN YouTube Search]		[http://www.youtube.com/results?search_query=Spatialtemporal+Spatial+Temporal+Spatio+Dynamic+Network+STDN YouTube Search]
	[http://www.google.com/search?q=Spatialtemporal+Spatial+Temporal+Spatio+Dynamic+Network+STDN+deep+machine+learning+ML ...Google search]		[http://www.google.com/search?q=Spatialtemporal+Spatial+Temporal+Spatio+Dynamic+Network+STDN+deep+machine+learning+ML ...Google search]

@@ Line 8: / Line 8: @@
 The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice, the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. [http://arxiv.org/abs/1803.01254 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction | H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li]
-http://www.frontiersin.org/files/Articles/323875/fnins-12-00331-HTML/image_t/fnins-12-00331-g001.gif
+http://www.plantcell.org/content/plantcell/25/6/2132/F1.medium.gif
 <youtube>V3BWJLg0L5w</youtube>

← Older revision		Revision as of 16:50, 13 January 2019
Line 8:		Line 8:
	The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice, the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. [http://arxiv.org/abs/1803.01254 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction \| H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li]		The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice, the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. [http://arxiv.org/abs/1803.01254 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction \| H. Yao, X. Tang, H. Wei, G. Zheng, and Z. Li]

		+	http://www.frontiersin.org/files/Articles/323875/fnins-12-00331-HTML/image_t/fnins-12-00331-g001.gif

	<youtube>V3BWJLg0L5w</youtube>		<youtube>V3BWJLg0L5w</youtube>

@@ Line 2: / Line 2: @@
 [http://www.google.com/search?q=Spatialtemporal+Spatial+Temporal+Spatio+Dynamic+Network+STDN+deep+machine+learning+ML ...Google search]
-* [Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning]
+* [[Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning]]
 * [[Memory Networks]]