課件分析machine learning2019s課件auto v

1、MORE ABOUTAUTO-ENCODERHung-yi Lee 李宏毅Auto-encoderAs close as possibleNNEncoderNNDecodervector More than minimizing reconstruction error More interpretable embeddingEmbedding, Latent Representation, Latent CodeWhat is good embedding? An embedding should represent the object.是一對(duì)不是一對(duì)NNEncoderNNEncoderD

2、iscriminatorimagey/nBeyond Reconstruction binary classifierloss of the classification task is Small The embeddings are representative.Say “Yes”Say “No”How to evaluate an encoder?Train to minimize NNEncoderNNEncoderDiscriminatorimagey/nBeyond Reconstruction binary classifierloss of the classification

3、 task is Small The embeddings are representative.Say “Yes”Say “No”How to evaluate an encoder?Train to minimize Large Not representativeNNEncoderNNEncoderDiscriminatorimagey/nBeyond Reconstruction binary classifierloss of the classification task is Small The embeddings are representative.How to evalu

4、ate an encoder?Train to minimize Large Not representativeTrain to minimize Train the encoder and discriminator to minimize (c.f. training encoder and decoder to minimize reconstruction error)Deep InfoMax (DIM)As close as possibleNNEncoderNNDecodervectorTypical auto-encoder is a special caseNNDecoder

5、vector-score(reconstruction error)DiscriminatorSequential Data Skip thoughtQuick thoughtA document is a sequence of sentences.currentpreviousnextcurrentnextrandomrandomSequential Data Contrastive Predictive Coding (CPC) Auto-encoderAs close as possibleNNEncoderNNDecodervector More than minimizing re

6、construction error More interpretable embeddingEmbedding, Latent Representation, Latent CodeFeature Disentangle An object contains multiple aspect information EncoderDecoderinput audioreconstructed Include phonetic information, speaker information, etc. EncoderDecoderinput sentencereconstructed Incl

7、ude syntactic information, semantic information, etc. Source: Feature Disentangle EncoderDecoderinput audioreconstructed speaker informationphonetic informationEncoder 1Decoderreconstructed speaker informationphonetic informationEncoder 2Feature Disentangle- Voice Conversion How are you?HelloEncoder

8、How are you?EncoderHelloDecoderHow are you?DecoderHelloFeature Disentangle- Voice Conversion How are you?HelloEncoderHow are you?EncoderHelloDecoderHow are you?How are you?Feature Disentangle- Voice Conversion The same sentence has different impact when it is said by different people.Do you want to

9、study a PhD?Go away!StudentStudentDo you want to study a PhD?新垣結(jié)衣新垣結(jié)衣(Aragaki Yui)Feature Disentangle- Adversarial Training How are you?EncoderHow are you?DecoderHow are you?SpeakerClassifierorLearn to fool the speaker classifier(Discriminator)Speaker classifier and encoder are learned iterativelyFe

10、ature Disentangle- Designed Network ArchitectureHow are you?Encoder 1= instance normalizationINEncoder 2How are you?DecoderINHow are you?(remove global information)How are you?Feature Disentangle- Designed Network ArchitectureHow are you?Encoder 1Encoder 2How are you?DecoderINAdaINHow are you?= inst

11、ance normalizationINAdaIN= adaptive instance normalization(remove global information)(only influence global information)Source Speaker Target Speaker Me (Never seen during training!)MeMeSource to TargetThanks Ju-chieh Chou for providing the results.MeFeature Disentangle - Adversarial Training Discre

12、te Representation Easier to interpret or clustering NNEncoderNNDecoder0.90.10.30.7One-hot1000NNEncoderNNDecoder0.90.10.30.7Binary 1001 11.01144.pdfnon differentiableDiscrete Representation Vector Quantized Variational Auto-encoder (VQVAE) NNEncoderNNDecodervectorvector 1Codebook(a set of vectors)vec

13、tor 2vector 3vector 4vector 5vector 3 For speech, the codebook represents phonetic informationCompute similarity Learn from dataThe most similar one is the input of decoder.Sequence as EmbeddingGRSummary?Seq2seqSeq2seqdocumentdocumentword sequenceOnly need a lot of documents to train the modelThis i

14、s a seq2seq2seq auto-encoder.Using a sequence of words as latent representation.not readable Sequence as EmbeddingGRSeq2seqSeq2seqword sequenceDHuman written summariesReal or notDiscriminatorLet Discriminator considers my output as realdocumentdocumentSummary?ReadableSequence as Embedding Document:澳

15、大利亞今天與澳大利亞今天與13個(gè)國(guó)家簽署了反興奮劑雙個(gè)國(guó)家簽署了反興奮劑雙邊協(xié)議邊協(xié)議,旨在加強(qiáng)體育競(jìng)賽之外的藥品檢查並共享研究成旨在加強(qiáng)體育競(jìng)賽之外的藥品檢查並共享研究成果果 Summary: Human:澳大利亞與澳大利亞與13國(guó)簽署反興奮劑協(xié)議國(guó)簽署反興奮劑協(xié)議 Unsupervised:澳大利亞加強(qiáng)體育競(jìng)賽之外的藥品檢查澳大利亞加強(qiáng)體育競(jìng)賽之外的藥品檢查 Document:中華民國(guó)奧林匹克委員會(huì)今天接到一九九二中華民國(guó)奧林匹克委員會(huì)今天接到一九九二年冬季奧運(yùn)會(huì)邀請(qǐng)函年冬季奧運(yùn)會(huì)邀請(qǐng)函,由於主席張豐緒目前正在中南美洲由於主席張豐緒目前正在中南美洲進(jìn)行友好訪問(wèn)進(jìn)行友好訪問(wèn),因此尚未決定是否

16、派隊(duì)赴賽因此尚未決定是否派隊(duì)赴賽 Summary: Human:一九九二年冬季奧運(yùn)會(huì)函邀我參加一九九二年冬季奧運(yùn)會(huì)函邀我參加 Unsupervised:奧委會(huì)接獲冬季奧運(yùn)會(huì)邀請(qǐng)函奧委會(huì)接獲冬季奧運(yùn)會(huì)邀請(qǐng)函感謝 王耀賢 同學(xué)提供實(shí)驗(yàn)結(jié)果Sequence as Embedding Document:據(jù)此間媒體據(jù)此間媒體27日?qǐng)?bào)道日?qǐng)?bào)道,印度尼西亞蘇門答臘島印度尼西亞蘇門答臘島的兩個(gè)省近日來(lái)連降暴雨的兩個(gè)省近日來(lái)連降暴雨,洪水泛濫導(dǎo)致塌方洪水泛濫導(dǎo)致塌方,到到26日為日為止至少已有止至少已有60人喪生人喪生,100多人失蹤多人失蹤 Summary: Human:印尼水災(zāi)造成印尼水災(zāi)造成60人死亡人死亡 Unsupervised:印尼門洪水泛濫導(dǎo)致塌雨印尼門洪水泛濫導(dǎo)致塌雨 Document:安徽省合肥市最近為領(lǐng)導(dǎo)幹部下基層做了新安徽省合肥市最近為領(lǐng)導(dǎo)幹部下基層做了新規(guī)定規(guī)定:一律輕車簡(jiǎn)從一律輕車簡(jiǎn)從,不準(zhǔn)搞迎來(lái)送往、不準(zhǔn)搞層層陪不準(zhǔn)搞迎來(lái)送往、不準(zhǔn)搞層層陪同同 Summary: Human:合肥規(guī)定領(lǐng)導(dǎo)幹部下基層活動(dòng)從簡(jiǎn)合肥規(guī)定領(lǐng)導(dǎo)幹部下基層活動(dòng)從簡(jiǎn) Unsupervised:合肥領(lǐng)導(dǎo)幹部下基層做搞迎來(lái)送往規(guī)定合肥領(lǐng)導(dǎo)幹部