版權(quán)說明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請進(jìn)行舉報(bào)或認(rèn)領(lǐng)
文檔簡介
1、TRAININGRECURRENTNEURALWKSbyIlyaSutskeverAthesissubmittedinconfmitywiththerequirementsfthedegreeofDoctofPhilosophyGraduateDepartmentofComputerScienceUniversityofTontoCopyrightc?2013byIlyaSutskeverAcknowledgementsBeingaPh
2、DstudentinthemachinelearninggroupoftheUniversityofTontowaslotsoffunjoiningitwasoneofthebestdecisionsthatIhaveevermade.IwanttothankmyadviserGeoffHinton.Geofftaughtmehowtoreallydoresearchourmeetingswerethehighlightofmyweek
3、.Heisanexcellentmentwhogavemethefreedomtheencouragementtopursuemyownideastheopptunitytoattendmanyconferences.Meimptantlyhegavemehisunfailinghelpsupptwheneveritwasneeded.Iamgratefulfhavingbeenhisstudent.Iamftunatetohavebe
4、enapartofsuchanincrediblyfantasticMLgroup.Itrulythinkso.Theatmospherefacultypostdocsstudentswereoutstinginalldimensionswithoutexaggeration.IwanttothankmycommitteeRadfdNealToniPitassiinparticularfagreeingtoreadmythesissoq
5、uickly.IwanttothankRichfenjoyableconversationsflettingmeattendtheZgroupmeetings.Iwanttothankthecurrentlearningstudentspostdocsfmakingthelearninglabsuchafunenvironment:AbdelRahmanMohamedAlexGravesAlexKrizhevskylieTangChri
6、sMaddisonDannyTarlowEmilyDentonGegeDahlJamesMartensJasperSnoekMaksVolkovsNavdeepJaitlyNitishSrivastavaVladMnih.IwanttothankmyofficematesKevinSwerskyLaurentlinTijmenTielemanfmakingmelookfwardtoarrivingtotheoffice.Ialsowan
7、ttothankthefmerstudentspostdocswhosetimeinthegroupoverlappedwithmine:AmitGruberriyMnihHugoLarochelleIainMurrayJimHuangInmarGivoniNikolaKaramanovRuslanSalakhutdinovRyanP.AdamsVinodNair.ItwaslotsoffunwkingwithChrisMaddison
8、inthesummerof2011.Iamdeeplyindebtedtomycollabats:riyMnihlieTangDannyTarlowGegeDahlGrahamTaylJamesCookJoshTenenbaumKevinSwerskyNitishSrivastavaRuslanSalakhutdinovRyanP.AdamsTimLillicrapTijmenTielemanTomaˇsMikolovVinodNair
9、especiallytoAlexKrizhevskyJamesMartens.IamgratefultoDannyTarlowfdiscoveringTtoReluPatrufstimulatingconversationsfkeepingourcomputerswkingsmoothlytoLunaKeshwahfherexcellentadministrativesuppt.Iwanttothankstudentsinothergr
10、oupsfmakingschoolevenmeenjoyable:AbeHeifetsAidaNematzadehAminTootoonchianFernoFlesMangasIzharWallachLenaSimineNicolinLibbyBarakMichaLivneMiskoDzambaMohammadNouziionBuskeSiavashKazemianSiavoshBenabbasTasosZouziasVaradaKol
11、hatkaYuliaEskinYuvalFilmusanyoneelseImighthavefgot.AveryspecialthanksgoestoAnnatKenfmakingthewritingofthethesismeenjoyablefproofreadingit.ButmostofallIwanttoexpressthedeepestgratitudetomyfamilyespeciallytomyparentswhohav
溫馨提示
- 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁內(nèi)容里面會(huì)有圖紙預(yù)覽,若沒有圖紙預(yù)覽就沒有圖紙。
- 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 眾賞文庫僅提供信息存儲(chǔ)空間,僅對用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理,對用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對任何下載內(nèi)容負(fù)責(zé)。
- 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時(shí)也不承擔(dān)用戶因使用這些下載資源對自己和他人造成任何形式的傷害或損失。
最新文檔
- deep learning (2015), y. lecun, y. bengio and g. hinton
- deep learning學(xué)習(xí)筆記整理系列
- 2018-深入學(xué)習(xí)keras先進(jìn)-advanced deep learning with keras
- neural networks and deep learning_ a textbook(2018)
- deep reinforcement learning hands-on - apply modern rl methods, with deep q-netw
- Shallow and Deep Learning for Robust Online Object Tracking.pdf
- big data analysis and deep learning applications - proceedings of the first inte
- paddlepaddle- towards a deep learning compiler for the cloud-于洋-
- evolutionary approach to machine learning and deep neural networks - neuro-evolu
- 畢業(yè)論文high school geography teaching strategies under the guidance of the deep learning theory
- learning2.0時(shí)代大學(xué)生學(xué)習(xí)能力研究
- ways to encourage students’ motivation of learning english激勵(lì)學(xué)生學(xué)習(xí)英語的方法
- Behaviors Modeling and Analysis of Big Data from Web Apps Using Machine Learning and Deep Rnn Techniques.pdf
- 一個(gè)牛人是這樣學(xué)習(xí)模擬電路的
- 大學(xué)生英語學(xué)習(xí)動(dòng)機(jī)的研究(a study on motivation of college students in english learning)
- q何謂學(xué)習(xí)(learning)與教學(xué)(instruction)
- 向騰訊學(xué)習(xí)騰訊q-learning
- 學(xué)習(xí)與記憶(learning & memory)
- 增強(qiáng)學(xué)習(xí)reinforcement learning經(jīng)典算法梳理
- rolling in deep
評論
0/150
提交評論