| A Nested Attention Neural Hybrid Model for Grammatical Error Correction ｜ ACL 2017 [SI9cTcyNVew].mp4 | 33.3 MB | | 71ff6a9c |
| A Principled Framework for Evaluating Summarizers Comparing Models of Summary Quality against Human [H3mHtNVlm4U].mp4 | 23.5 MB | | ae256aab |
| A Two stage Parsing Method for Text level Discourse Analysis ｜ ACL 2017 ｜ Outstanding Paper [K7Ouk3BI034].mp4 | 17.8 MB | | d4353ce0 |
| Abstractive Document Summarization with a Graph Based Attentional Neural Model ｜ ACL 2017 [TGx-5gkSOI4].mp4 | 70.2 MB | | 3af1a4da |
| Adversarial Multi task Learning for Text Classification ｜ ACL 2017 ｜ Outstanding Paper [eM14H0wH4Vs].mp4 | 32.2 MB | | 9f1d9174 |
| An Unsupervised Neural Attention Model for Aspect Extraction ｜ ACL 2017 [0tSIkiTWBx0].mp4 | 29 MB | | c5d4caf4 |
| Attention over Attention Neural Networks for Reading Comprehension ｜ ACL 2017 ｜ Outstanding Paper [iJsoWwtplSI].mp4 | 29.6 MB | | 01a576cd |
| Cross Sentence N ary Relation Extraction with Graph LSTMs ｜ ACL 2017 ｜ Outstanding Paper [jiRzeXXzS6Q].mp4 | 42.5 MB | | 2360fbaf |
| Deep Keyphrase Generation ｜ ACL 2017 ｜ Outstanding Paper [p9vChQaa_M8].mp4 | 30.6 MB | | e16548df |
| Discourse Mode Identification in Essays ｜ ACL 2017 ｜ Outstanding Paper [5tRuCBXvAPA].mp4 | 33.5 MB | | fe747e4b |
| Diversity driven attention model for query based abstractive summarization ｜ ACL 2017 [XKSUtxC21F4].mp4 | 32.5 MB | | 0b44997c |
| EmoNet Fine Grained Emotion Detection with Gated Recurrent Neural Networks ｜ ACL 2017 [mkGIKOpsD9w].mp4 | 50.6 MB | | da580122 |
| Enriching Word Vectors with Subword Information ｜ ACL 2017 ｜ Outstanding Paper [tGQKjJQt7oQ].mp4 | 28.5 MB | | 6d8dd639 |
| Exploring Neural Text Simplification Models ｜ ACL 2017 ｜ Outstanding Paper [kfNVNCQ2RJw].mp4 | 21.2 MB | | f8c7a1cc |
| Friendships, Rivalries, and Trysts Characterizing Relations between Ideas in Texts Chenhao Tan, [kgMhT7qtkGI].mp4 | 41.3 MB | | 48036eb5 |
| Get To The Point Summarization with Pointer Generator Networks ｜ ACL 2017 ｜ Stanford [eUu6DpXBB2g].mp4 | 26.8 MB | | b808b04e |
| Handling Cold Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors [kNAWyqe6oi0].mp4 | 22.3 MB | | 92e06b72 |
| Joint Modeling of Content and Discourse Relations in Dialogues ｜ ACL 2017 [CiLxQehELt4].mp4 | 31.8 MB | | ff97628a |
| Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification [1YFYLli9RbI].mp4 | 28.7 MB | | 907b4b61 |
| Lecture 10 — Why Teleports Solve the Problem ｜ Stanford University [UZePPh340sU].mp4 | 32.2 MB | | 59184d82 |
| Lecture 11 — How we Really Compute PageRank ｜ Stanford University [E9aoTVmQvok].mp4 | 33.8 MB | | ab3a7ba6 |
| Lecture 3 — Scheduling and Data Flow ｜ Stanford University [uRjvVq1Jd-M].mp4 | 37.4 MB | | 9ae320b1 |
| Lecture 4 — Combiners and Partition Functions (Advanced) ｜ Stanford University [rUcBgSe6M4M].mp4 | 35.1 MB | | 2f11d399 |
| Lecture 5 — Link Analysis and PageRank ｜ Stanford University [fL41WSVDunM].mp4 | 25.4 MB | | 1895352c |
| Lecture 6 — PageRank The Flow Formulation ｜ Stanford University [1nLV8FEaZD0].mp4 | 18.1 MB | | 7408b531 |
| Lecture 7 — PageRank The Matrix Formulation ｜ Stanford University [3_1h13PJkUs].mp4 | 23.1 MB | | d55499e2 |
| Lecture 8 — PageRank Power Iteration ｜ Stanford University [VpiyOxiVmCg].mp4 | 28.8 MB | | b8f4ed53 |
| Lecture 9 — Doc Length Normalization ｜ UIUC [tKTpCkc2XEo].mp4 | 32.8 MB | | 828b2576 |
| Lecture 9 — PageRank - The Google Formulation ｜ Stanford University [ytjf6zYDd4s].mp4 | 24.7 MB | | 996e1859 |
| Lecture 1 — Distributed File Systems ｜ Stanford University [xoA5v9AO7S0].mp4 | 36.8 MB | | 780471cb |
| Lecture 1 — Human Computer Interaction ｜ Stanford University [WW1g3UT2zww].mp4 | 6.48 MB | | b2ea3ae9 |
| Lecture 1 — Introduction - Natural Language Processing ｜ University of Michigan [n25JjoixM3I].mp4 | 17.2 MB | | f83961b2 |
| Lecture 1 — Natural Language Content Analysis ｜ UIUC [A6NEmoeqUnU].mp4 | 42.7 MB | | 0ee4ebf3 |
| Lecture 1 — Overview Text Mining and Analytics - Part 1 [Uqs0GewlMkQ].mp4 | 19.3 MB | | e5564f4e |
| Lecture 1.1 — Why do we need machine learning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [OVwEeSsSCHE].mp4 | 20.2 MB | | d655492a |
| Lecture 1.2 — What are neural networks — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [jNBYZbDWyQk].mp4 | 13.5 MB | | 53ed17b2 |
| Lecture 1.3 — Some simple models of neurons — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [VA9niXgGOsQ].mp4 | 12 MB | | da70e159 |
| Lecture 1.4 — A simple example of learning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [mnTJezQOIDU].mp4 | 8.96 MB | | dec9a706 |
| Lecture 1.5 — Three types of learning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [nrkpEx7tA2Y].mp4 | 14.4 MB | | 7b4ad3b0 |
| Lecture 10 — Implementation of TR Systems ｜ UIUC [DWSnvppnspY].mp4 | 36 MB | | 5c602c84 |
| Lecture 10 — Morphology and the Lexicon - Natural Language Processing ｜ Michigan [CzMDw-hH7B0].mp4 | 49.7 MB | | 17b65ec4 |
| Lecture 10 — Storyboards, Paper Prototypes, and Mockups ｜ HCI ｜ Stanford University [z4glsttyxw8].mp4 | 25.3 MB | | 8c6a7600 |
| Lecture 10 — Syntagmatic Relation Discovery Entropy ｜ UIUC [TLXJAvV6tMo].mp4 | 16.5 MB | | 01a97206 |
| Lecture 10.1 — Why it helps to combine models — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [kZ7JJOMt5Kw].mp4 | 18.4 MB | | 66ba248f |
| Lecture 10.2 — Mixtures of Experts — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [FxrTtRvYQWk].mp4 | 17.2 MB | | b2ffbafa |
| Lecture 10.3 — The idea of full Bayesian learning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [1A6Md5ZYyW0].mp4 | 8.85 MB | | 55a83878 |
| Lecture 10.4 — Making full Bayesian learning practical — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [RsC9xfHYYH0].mp4 | 8.16 MB | | 6550292e |
| Lecture 10.5 — Dropout — [ Deep Learning ｜ Geoffrey Hinton ｜ Toronto ] [iCbVPfk_5CQ].mp4 | 11.5 MB | | fd270b6a |
| Lecture 11 — Faking it - Wizard of Oz ｜ HCI Course ｜ Stanford University [JKaufIzdHHE].mp4 | 40.5 MB | | 85246d8b |
| Lecture 11 — Morphological Similarity (Stemming) - Natural Language Processing [hdwhI3VYO5A].mp4 | 38.8 MB | | 2182d2a7 |
| Lecture 11 — Syntagmatic Relation Discovery Conditional Entropy ｜ UIUC [Lv7poltbGKw].mp4 | 23.9 MB | | b5ac3aa4 |
| Lecture 11 —System Implementation Inverted Index Construction ｜ UIUC [CDzxiWZEuCs].mp4 | 26.3 MB | | c7f5db5d |
| Lecture 11.1 — Hopfield Nets — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [Rs1XMS8NqB4].mp4 | 17.1 MB | | 1f8344ad |
| Lecture 11.2 — Dealing with spurious minima — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [HJfhdksIqUE].mp4 | 14.9 MB | | e15841e7 |
| Lecture 11.3 — Hopfield nets with hidden units— [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [GZTmqMSxAR4].mp4 | 13.4 MB | | 03b6cd94 |
| Lecture 11.4 — Using stochastic units to improve search — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [4vBqFO9bPeg].mp4 | 13.5 MB | | a22c62e5 |
| Lecture 11.5 — How a Boltzmann machine models data — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [kytxEr0KK7Q].mp4 | 17.3 MB | | b448f119 |
| Lecture 12 — Finding Similar Sets ｜ Stanford University [ZsXIuJtjsWk].mp4 | 34 MB | | 805b467b |
| Lecture 12 — Faking it - Video Prototyping ｜ HCI Course ｜ Stanford University [9IKb1yttz4s].mp4 | 47.2 MB | | 19e06d66 |
| Lecture 12 — Spelling Similarity (Edit Distance) - Natural Language Processing [1KySp2fTuag].mp4 | 45.4 MB | | 3e698605 |
| Lecture 12 — Syntagmatic Relation Discovery Mutual Information - Part 1 ｜ UIUC [C5hWEhqTGWw].mp4 | 18.1 MB | | 29618df5 |
| Lecture 12 — System Implementation Fast Search ｜ UIUC [FbF-E8FlgVo].mp4 | 29.6 MB | | 376d794b |
| Lecture 12.1 — Boltzmann machine learning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [2k9XTr_jNfE].mp4 | 16.3 MB | | f5b75d55 |
| Lecture 12.2 — More efficient ways to get the statistics — [ Deep Learning ｜ Hinton ｜ UofT ] [CkZ9HA6KUnA].mp4 | 23 MB | | d2584c90 |
| Lecture 12.3 — Restricted Boltzmann Machines — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [EZOpZzUKl48].mp4 | 14.5 MB | | cbf31c90 |
| Lecture 12.4 — An example of RBM learning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [iHaS6O1eox4].mp4 | 9.86 MB | | 763e03aa |
| Lecture 12.5 — RBMs for collaborative filtering — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [on5lto0rG48].mp4 | 10.7 MB | | 6d91cd91 |
| Lecture 13 — Minhashing ｜ Mining of Massive Datasets ｜ Stanford University [ZjdQD79Psi0].mp4 | 49.8 MB | | 83b31656 |
| Lecture 13 — Creating and Comparing Alternatives ｜ HCI ｜ Stanford University [tWHdYjZz_tM].mp4 | 27.4 MB | | b3558d1c |
| Lecture 13 — Evaluation of TR Systems ｜ UIUC [rKVGfpIlInQ].mp4 | 18.5 MB | | 798955d6 |
| Lecture 13 — NACLO - Natural Language Processing [Dm3GswBjgog].mp4 | 8.64 MB | | c600ef62 |
| Lecture 13 — Syntagmatic Relation Discovery Mutual Information - Part 2 ｜ UIUC [bFGuwO5WYIQ].mp4 | 13.3 MB | | fd60c33f |
| Lecture 13.1 — The ups and downs of backpropagation — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [lDFY8vQe6-g].mp4 | 14.2 MB | | 78fc72d7 |
| Lecture 13.2 — Belief Nets — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [1CgojqlHrcE].mp4 | 23.9 MB | | c95a9275 |
| Lecture 14 — Locality Sensitive Hashing ｜ Stanford University [e8dA0tscrCM].mp4 | 57.1 MB | | 7151e4b0 |
| Lecture 14 — Evaluation of TR Systems Basic Measures ｜ UIUC [6X-COr3elcg].mp4 | 22.2 MB | | 14d4346a |
| Lecture 14 — Heuristic Evaluation - Why and How ｜ HCI Course ｜ Stanford University [J09MeSfOTJE].mp4 | 42.8 MB | | 93a33ee7 |
| Lecture 14 — Preprocessing - Natural Language Processing [0xgH2WCRGww].mp4 | 23.7 MB | | b75ee0a9 |
| Lecture 14 — Topic Mining and Analysis Motivation and Task Definition ｜ UIUC [pbgXwa_kmlE].mp4 | 16 MB | | a8308e4c |
| Lecture 14.1 — Learning layers of features by stacking RBMs — [ Deep Learning ｜ Hinton ｜ UofT ] [Y3beRvYSA90].mp4 | 22.6 MB | | e3263d16 |
| Lecture 14.2 — Discriminative learning for DBNs — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [QCBkbDpsheQ].mp4 | 13.2 MB | | 14273b84 |
| Lecture 14.3 — Discriminative fine tuning — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [YPQjud6JaSE].mp4 | 11.7 MB | | 965ed132 |
| Lecture 14.4 — Modeling real valued data with an RBM — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [SnbfQwJLNk8].mp4 | 12.8 MB | | a7871475 |
| Lecture 14.5 — RBMs are infinite sigmoid belief nets — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [lgApksxm6VE].mp4 | 22.7 MB | | 16da2e88 |
| Lecture 15 — Applications of LSH ｜ Stanford University [QzXE8JDGxus].mp4 | 19.5 MB | | 14c74696 |
| Lecture 15 — Semantic Similarity- Synonymy and other Semantic Relations - NLP [PxgkddPbjrM].mp4 | 36.6 MB | | 5a6af017 |
| Lecture 15 — Topic Mining and Analysis Term as Topic ｜ UIUC [ONzpEPngVgg].mp4 | 17 MB | | e56a2480 |
| Lecture 15 —Evaluation of TR Systems Evaluating Ranked Lists -- Part 1 ｜ UIUC [jB3cnavRw-0].mp4 | 21.8 MB | | 571bc68f |
| Lecture 15.1 — From PCA to autoencoders — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [PSOt7u8u23w].mp4 | 11 MB | | e348b8b4 |
| Lecture 15.2 — Deep autoencoders — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [6jhhIPdgkp0].mp4 | 5.42 MB | | c75ac3ff |
| Lecture 15.3 — Deep autoencoders for document retrieval — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [ZCNbjpcX0yg].mp4 | 11.8 MB | | f1233d43 |
| Lecture 15.4 — Semantic Hashing — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [3BDc0H9C9dw].mp4 | 10.5 MB | | 9bac86bb |
| Lecture 15.5 — Learning binary codes for image retrieval — [ Deep Learning ｜ Hinton ｜ UofT ] [j1ry6Pg7X14].mp4 | 13.5 MB | | fd89f23d |
| Lecture 15.6 — Shallow autoencoders for pre training — [ Deep Learning ｜ Geoffrey Hinton ｜ UofT ] [xjlvVfEbhz4].mp4 | 9.75 MB | | cfff61ac |
| Lecture 16 — Fingerprint Matching ｜ Stanford University [HjaRHQONwBE].mp4 | 11.9 MB | | 6f25fd8f |
| Lecture 16 — Design Heuristics - (Part 2) ｜ HCI Course ｜ Stanford University [eWVw5HLZhuk].mp4 | 50.7 MB | | af4cff9e |
| Lecture 16 — Evaluation of TR Systems Evaluating Ranked Lists -- Part 2 ｜ UIUC [YH00rsmoO6Y].mp4 | 18.3 MB | | 99b02dc9 |
| Lecture 16 — Thesaurus-based Word Similarity Methods - Natural Language Processing [eM62rKR1TlE].mp4 | 19.5 MB | | fcaa3481 |
| Lecture 16 — Topic Mining and Analysis Probabilistic Topic Models ｜ UIUC [CpqxTj_m4Vw].mp4 | 29 MB | | 8bb1971d |
| Lecture 16.1 — Learning a joint model of images and captions — [ Deep Learning ｜ Hinton ｜ UofT ] [kVuF-9BaDLs].mp4 | 16.4 MB | | 1a4ef5e9 |
|
