Yang Zhang (Work Log) - Revision history

MichelleH at 16:03, 9 November 2017

2017-11-09T16:03:04Z

2017-09-28T21:58:31Z

2017-09-26T19:09:12Z

2017-09-19T21:01:25Z

2017-09-19T20:53:07Z

Created page with "Category:Work Log"

New page

[[Category:Work Log]]

@@ Line 1: / Line 1: @@
-/19/2017 accounts setup and get familiar with the rules
+===Fall 2017===
-/21/2017 start to build two different kinds of deep neural networks (Convolutional and LSTM) to classify the companies' industry, specifically for the file "Descriptions.txt"
+[[Yang Zhang]] [[Work Logs]] [[Yang Zhang (Work Log)|(log page)]]
-/22/2017 the two models both can achieve 90+% training accuracy and ~60% testing accuracy. Notice that the task is hard even for humans and thus 60% is acceptable, plus the baseline is under 10% for random guessing
+-09-28: the LSTM model achieves 67% testing accuracy
-/26/2017 modify the previous model and train on the "longdescriptionindu.txt"
+-09-26: modify the previous model and train on the "longdescriptionindu.txt"
-/28/2017 the LSTM model achieves 67% testing accuracy
+-09-22: the two models both can achieve 90+% training accuracy and ~60% testing accuracy. Notice that the task is hard even for humans and thus 60% is acceptable, plus the baseline is under 10% for random guessing
 [[Category:Work Log]]

@@ Line 5: / Line 5: @@
 /22/2017 the two models both can achieve 90+% training accuracy and ~60% testing accuracy. Notice that the task is hard even for humans and thus 60% is acceptable, plus the baseline is under 10% for random guessing
-/22/2017 document
+/26/2017 modify the previous model and train on the "longdescriptionindu.txt"
 [[Category:Work Log]]

← Older revision		Revision as of 19:09, 26 September 2017
Line 1:		Line 1:
	09/19/2017 accounts setup and get familiar with the rules		09/19/2017 accounts setup and get familiar with the rules

		+	09/21/2017 start to build two different kinds of deep neural networks (Convolutional and LSTM) to classify the companies' industry, specifically for the file "Descriptions.txt"
		+
		+	09/22/2017 the two models both can achieve 90+% training accuracy and ~60% testing accuracy. Notice that the task is hard even for humans and thus 60% is acceptable, plus the baseline is under 10% for random guessing
		+
		+	09/22/2017 document


	[[Category:Work Log]]		[[Category:Work Log]]

← Older revision		Revision as of 21:01, 19 September 2017
Line 1:		Line 1:
		+	09/19/2017 accounts setup and get familiar with the rules
		+
		+
		+
	[[Category:Work Log]]		[[Category:Work Log]]