2015年9月9日 (三) 00:56的版本 （查看源代码） Xingchao（讨论 | 贡献） （以“==Speech Processing == === AM development === ==== Environment ==== * grid-12 sometimes does not work ==== RNN AM==== *train monophone RNN --zhiyuan *train using...”为内容创建页面）		2015年9月14日 (一) 09:01的最后版本 （查看源代码） Zxw（讨论 | 贡献） （→‎Speech Processing）
（2位用户的3个中间修订版本未显示）
第3行：		第3行：
	==== Environment ====		==== Environment ====
−	* grid-12 sometimes does not work	+	* grid-12 GPU is transferred to grid-18
−		+	* buy a 970 GPU
	==== RNN AM====		==== RNN AM====
	*train monophone RNN --zhiyuan		*train monophone RNN --zhiyuan
−	*train using large dataset--mengyuan	+	:* decode using 5-gram
−	*write code to tune learning rate--zhiyong	+	:* the train method of batch
		+	* train using large dataset--mengyuan
		+	* write code to tune learning rate --zhiyong
		+	:* has completed Nestrov/Adagrad/Adagrad-max
		+	:* has unstable phenomenon
		+	:* completed adam,adadeta,adam-max --Xiangyu,Zhiyong
		+	:* reproduce PSO --Xiangyu
	==== Mic-Array ====		==== Mic-Array ====
第19行：		第25行：
	* acoustic feature based submodular using Pingan dataset --zhiyong		* acoustic feature based submodular using Pingan dataset --zhiyong
	* write code to speed up --zhiyong		* write code to speed up --zhiyong
−
	====RNN-DAE(Deep based Auto-Encode-RNN)====		====RNN-DAE(Deep based Auto-Encode-RNN)====
−	* hold	+	* RNN-DAE has worse performance than DNN-DAE because training dataset is small
−	* deliver to mengyuan, xuewei	+	* extract real room impulse to generate WSJ reverberation data, and then train RNN-DAE
−	:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261	+
−		+
	===Ivector&Dvector based ASR===		===Ivector&Dvector based ASR===
−	* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric	+	* Cluster the speakers to speaker-cluster
−	:*hold	+	:* hold
−	* dark-konowlege using i-vector	+	* dark knowledge
		+	:* has much worse performance than baseline (EER: base 29%  dark knowledge 48%)
	* RNN ivector		* RNN ivector
−	* binary ivector	+	:* hold
		+	* binary ivector done
		+	* metric learning
	===language vector===		===language vector===
	* hold		* hold
	* train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan		* train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
−	:* hold
	* write a paper--zhiyuan		* write a paper--zhiyuan
	* RNN language vector		* RNN language vector
	:* hold		:* hold
−
	===multi-GPU====		===multi-GPU====
	* multi-stream training --Sheng Su		* multi-stream training --Sheng Su
−	* solve the problem of buffer--Mengyuan	+	:* two GPUs work well, but four GPUs divergent
		+	* solve the problem of buffer--Mengyuan, Sheng Su
		+
		+	===Neutral picture style transfer===
		+	* reproduced the result of the paper "A neutral algorithm of artistic style" --Zhiyuan, Xuewei
		+	* while subject to the GPU's memory, limited to inception net with sgd optimizer (VGG network with the default L-BFGS optimizer consumes very much memory, which is better)
	==Text Processing==		==Text Processing==
第124行：		第133行：
	:* add more feature		:* add more feature
	==rule combination==		==rule combination==
−	* rule analysis	+	* GA method to optimize the model
		+
	==basic rule==		==basic rule==
	* classical tenth model		* classical tenth model
−		+	==multiple-factor==
		+	* add more factor
		+	* use sparse model
	==display==		==display==
	* bug fixed		* bug fixed
−	:* index calculation
	:* buy rule fixed		:* buy rule fixed
−	* document
	==data==		==data==
	* data api		* data api
−	* download data	+	:* download the future data and factor data

---

2015年9月14日 (一) 09:01的最后版本

Speech Processing

AM development

Environment

• grid-12 GPU is transferred to grid-18
• buy a 970 GPU

RNN AM

• train monophone RNN --zhiyuan

• decode using 5-gram
• the train method of batch

• train using large dataset--mengyuan
• write code to tune learning rate --zhiyong

• has completed Nestrov/Adagrad/Adagrad-max
• has unstable phenomenon
• completed adam,adadeta,adam-max --Xiangyu,Zhiyong
• reproduce PSO --Xiangyu

Mic-Array

• hold
• compute EER with kaldi

====Data selection unsupervised learning

• hold
• acoustic feature based submodular using Pingan dataset --zhiyong
• write code to speed up --zhiyong

RNN-DAE(Deep based Auto-Encode-RNN)

• RNN-DAE has worse performance than DNN-DAE because training dataset is small
• extract real room impulse to generate WSJ reverberation data, and then train RNN-DAE

Ivector&Dvector based ASR

• Cluster the speakers to speaker-cluster

• hold

• dark knowledge

• has much worse performance than baseline (EER: base 29% dark knowledge 48%)

• RNN ivector

• hold

• binary ivector done
• metric learning

language vector

• hold
• train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
• write a paper--zhiyuan
• RNN language vector

• hold

multi-GPU=

• multi-stream training --Sheng Su

• two GPUs work well, but four GPUs divergent

• solve the problem of buffer--Mengyuan, Sheng Su

Neutral picture style transfer

• reproduced the result of the paper "A neutral algorithm of artistic style" --Zhiyuan, Xuewei
• while subject to the GPU's memory, limited to inception net with sgd optimizer (VGG network with the default L-BFGS optimizer consumes very much memory, which is better)

Text Processing

RNN LM

• character-lm rnn(hold)
• lstm+rnn

• check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

Neural Based Document Classification

• (hold)

RNN Rank Task

• Test.
• Paper: RNN Rank Net.

• (hold)
• Output rank information.

Graph RNN

• Entity path embeded to entity.

• (hold)

RNN Word Segment

• Set bound to word segment.

• (hold)

Seq to Seq(09-15)

• Review papers.
• Reproduce baseline. (08-03 <--> 08-17)

Order representation

• Nested Dropout

• semi-linear --> neural based auto-encoder.

• modify the objective function(hold)

Balance Representation

• Find error signal

Recommendation

• Reproduce baseline.

• LDA matrix dissovle.
• LDA (Text classification & Recommendation System) --> AAAI

RNN based QA

• Read Source Code.
• Attention based QA.
• Coding.

RNN Poem Process

• Seq based BP.

• (hold)

Text Group Intern Project

Buddhist Process

• (hold)

RNN Poem Process

• Done by Haichao yu & Chaoyuan zuo Mentor : Tianyi Luo.

RNN Document Vector

• (hold)

Image Baseline

• Demo Release.
• Paper Report.

• Read CNN Paper.

Text Intuitive Idea

Trace Learning

• (Hold)

Match RNN

• (Hold)

financial group

model research

• RNN

• online model, update everyday
• modify cost function and learning method
• add more feature

rule combination

• GA method to optimize the model

basic rule

• classical tenth model

multiple-factor

• add more factor
• use sparse model

display

• bug fixed

• buy rule fixed

data

• data api

• download the future data and factor data