NLP Specialization

Responsible	Administrator
Last Update	05/18/2023
Members	0

Course
Reviews

Intermediate

- README
  
  Preview
- utils2.py
  
  Preview
- punkt.zip
  
  Preview
- Untitled.ipynb
  
  Preview
Week1
- 1. Welcome to the NLP Specialization.mp4
  
  Preview
- 2. Welcome to Course 1 .mp4
  
  Preview
- 3. Supervised ML _ Sentiment Analysis .mp4
  
  Preview
- 4. Vocabulary _ Feature Extraction .mp4
  
  Preview
- 5. Negative and Positive Frequencies .mp4
  
  Preview
- 6. Feature Extraction with Frequencies .mp4
  
  Preview
- 7. Preprocessing .mp4
  
  Preview
- 8. Putting it All Together.mp4
  
  Preview
- 9. Logistic Regression Overview.mp4
  
  Preview
- 10. Logistic Regression- Training .mp4
  
  Preview
- 11. Logistic Regression- Testing.mp4
  
  Preview
- 12. Logistic Regression- Cost Function .mp4
  
  Preview
- Acknowledgement - Ken Church
  
  Preview
- Acknowledgement - Ken Church _ Coursera.pdf
  
  Preview
- Andrew Ng with Chris Manning.mp4
  
  Preview
Reading
- 1. Supervised ML _ Sentiment Analysis.pdf
  
  Preview
- 2. Vocabulary _ Feature Extraction.pdf
  
  Preview
- 3. Feature Extraction with Frequencies.pdf
  
  Preview
- 4. Preprocessing.pdf
  
  Preview
- 5. Putting it all together.pdf
  
  Preview
- 6. Logistic Regression Overview.pdf
  
  Preview
- 7. Logistic Regression Overview.pdf
  
  Preview
- 8. Logistic Regression_ Training.pdf
  
  Preview
- 9. Logistic Regression_ Testing.pdf
  
  Preview
- 10. Optional Logistic Regression_ Cost Function.pdf
  
  Preview
- 11. Optional Logistic Regression_ Gradient.pdf
  
  Preview
Week2
- 1. Probability and Bayes’ Rule.mp4
  
  Preview
- 2. Bayes’ Rule.mp4
  
  Preview
- 3. Naïve Bayes Introduction .mp4
  
  Preview
- 4. Laplacian Smoothing .mp4
  
  Preview
- 5. Log Likelihood, Part 1 .mp4
  
  Preview
- 6. Log Likelihood, Part 2 .mp4
  
  Preview
- 7. Training Naïve Bayes .mp4
  
  Preview
- 8. Testing Naïve Bayes .mp4
  
  Preview
- 9. Applications of Naïve Bayes .mp4
  
  Preview
- 10. Naïve Bayes Assumptions.mp4
  
  Preview
- 11. Error Analysis .mp4
  
  Preview
Reading
- 1. Probability and Bayes’ Rule.pdf
  
  Preview
- 2. Bayes_ Rule.pdf
  
  Preview
- 3. Naive Bayes Introduction.pdf
  
  Preview
- 4. Laplacian Smoothing.pdf
  
  Preview
- 5. Log Likelihood, Part 1.pdf
  
  Preview
- 6. Log Likelihood Part 2.pdf
  
  Preview
- 7. Training naïve Bayes.pdf
  
  Preview
- 8. Testing naïve Bayes.pdf
  
  Preview
- 9. Naïve Bayes Assumptions.pdf
  
  Preview
- 10. Error Analysis.pdf
  
  Preview
Week3
- 1. Vector Space Models.mp4
  
  Preview
- 2. Word by Word and Word by Doc..mp4
  
  Preview
- 3. Euclidean Distance .mp4
  
  Preview
- 4. Cosine Similarity- Intuition .mp4
  
  Preview
- 5. Cosine Similarity .mp4
  
  Preview
- 6. Manipulating Words in Vector Spaces.mp4
  
  Preview
- 7. Visualization and PCA .mp4
  
  Preview
- 8. PCA Algorithm .mp4
  
  Preview
NLP_C1_W3
- catdog.png
  
  Preview
- GaussianScatterPCA.svg
  
  Preview
- NLP_C1_W3_lecture_nb_01.ipynb
  
  Preview
- NLP_C1_W3_lecture_nb_02.ipynb
  
  Preview
- NLP_C1_W3_lecture_nb_03.ipynb
  
  Preview
- pca.jpeg
  
  Preview
- word_embeddings_subset.p
  
  Preview
Week4
- 1. Overview.mp4
  
  Preview
- 2. Transforming word vectors .mp4
  
  Preview
- 3. K-nearest neighbors .mp4
  
  Preview
- 4. Hash tables and hash functions .mp4
  
  Preview
- 5. Locality sensitive hashing.mp4
  
  Preview
- 6. Multiple Planes.mp4
  
  Preview
- 7. Approximate nearest neighbors .mp4
  
  Preview
- 8. Searching documents .mp4
  
  Preview
- Andrew Ng with Kathleen McKeown.mp4
  
  Preview
Week1
- 1. Intro to Course 2.mp4
  
  Preview
- 2. Overview.mp4
  
  Preview
- 3. Autocorrect.mp4
  
  Preview
- 4. Building the model.mp4
  
  Preview
- 5. Building the model II.mp4
  
  Preview
- 6. Minimum edit distance.mp4
  
  Preview
- 7. Minimum edit distance algorithm.mp4
  
  Preview
- 8. Minimum edit distance algorithm II.mp4
  
  Preview
- 9. Minimum edit distance algorithm III.mp4
  
  Preview
C2_W1_Assignment
- auto-correct.png
  
  Preview
- C2_W1_Assignment.ipynb
  
  Preview
- EditDistExample1.PNG
  
  Preview
- EditDistFill2.PNG
  
  Preview
- EditDistInit4.PNG
  
  Preview
- GenericListComp3.PNG
  
  Preview
- ListComp2.PNG
  
  Preview
- Splits1.PNG
  
  Preview
- Switches1.PNG
  
  Preview
- Untitled.ipynb
  
  Preview
NLP_C2_W1
- NLP_C2_W1_lecture_nb_01.ipynb
  
  Preview
- NLP_C2_W1_lecture_nb_02.ipynb
  
  Preview
Week2
- 1. Part of Speech Tagging.mp4
  
  Preview
- 2. Markov Chains.mp4
  
  Preview
- 3. Markov Chains and POS Tags.mp4
  
  Preview
- 4. Hidden Markov Models.mp4
  
  Preview
- 5. Calculating Probabilities.mp4
  
  Preview
- 6. Populating the Transition Matrix.mp4
  
  Preview
- 7. Populating the Emission Matrix.mp4
  
  Preview
- 8. The Viterbi Algorithm.mp4
  
  Preview
- 9. Viterbi- Initialization.mp4
  
  Preview
- 10. Viterbi- Forward Pass.mp4
  
  Preview
- 11. Viterbi- Backward Pass.mp4
  
  Preview
NLP_C2_W2
- NLP_C2_W2_lecture_notebook_numpy.ipynb
  
  Preview
- NLP_C2_W2_lecture_notebook_strings_tags.ipynb
  
  Preview
- Untitled.ipynb
  
  Preview
- WSJ_02-21.pos
  
  Preview
Week3
- 1. N-Grams- Overview.mp4
  
  Preview
- 2. N-grams and Probabilities.mp4
  
  Preview
- 3. Sequence Probabilities.mp4
  
  Preview
- 4. Sequence Probabilities.mp4
  
  Preview
- 5. The N-gram Language Model.mp4
  
  Preview
- 6. Language Model Evaluation.mp4
  
  Preview
- 7. Out of Vocabulary Words.mp4
  
  Preview
- 8. Smoothing.mp4
  
  Preview
- 9. Week Summary.mp4
  
  Preview
C2_W3_Assignment
- C2_W3_Assignment.ipynb
  
  Preview
- NLP_C2_W3_lecture_nb_01.ipynb
  
  Preview
- NLP_C2_W3_lecture_nb_02.ipynb
  
  Preview
- NLP_C2_W3_lecture_nb_03.ipynb
  
  Preview
- stanford.png
  
  Preview
NLP_C2_W3
- NLP_C2_W3_lecture_nb_01.ipynb
  
  Preview
- NLP_C2_W3_lecture_nb_02.ipynb
  
  Preview
- NLP_C2_W3_lecture_nb_03.ipynb
  
  Preview
Week4
- 1. Overview.mp4
  
  Preview
- 2. Basic Word Representations.mp4
  
  Preview
- 3. Word Embeddings.mp4
  
  Preview
- 4. How to Create Word Embeddings .mp4
  
  Preview
- 5. Word Embedding Methods .mp4
  
  Preview
- 6. Continuous Bag-of-Words Model .mp4
  
  Preview
- 7. Cleaning and Tokenization .mp4
  
  Preview
- 8. Sliding Window of Words in Python.mp4
  
  Preview
- 9. Transforming Words into Vectors .mp4
  
  Preview
- 10. Architecture of the CBOW Model .mp4
  
  Preview
- 11. Architecture of the CBOW Model- Dimensions.mp4
  
  Preview
- 12. Architecture of the CBOW Model- Dimensions 2 .mp4
  
  Preview
- 13. Architecture of the CBOW Model- Activation Functions .mp4
  
  Preview
- 14. Training a CBOW Model- Cost Function .mp4
  
  Preview
- 15. Training a CBOW Model- Cost Function .mp4
  
  Preview
- 16. Training a CBOW Model- Backpropagation and Gradient Descent .mp4
  
  Preview
- 17. Extracting Word Embedding Vectors .mp4
  
  Preview
- 18. Evaluating Word Embeddings- Intrinsic Evaluation .mp4
  
  Preview
- 19. Evaluating Word Embeddings- Extrinsic Evaluation .mp4
  
  Preview
- 20. Conclusion .mp4
  
  Preview
tokenizers
- punkt.zip
  
  Preview
- Untitled.ipynb
  
  Preview
- utils2.py
  
  Preview
- word2.png
  
  Preview
Week1
- 1. Course 3 Introduction.mp4
  
  Preview
- 2. Neural Networks for Sentiment Analysis .mp4
  
  Preview
- 3. Trax- Neural Networks .mp4
  
  Preview
- 4. Why we recommend Trax.mp4
  
  Preview
- 5. Trax- Layers .mp4
  
  Preview
- 6. Dense and ReLU Layers .mp4
  
  Preview
- 7. Serial Layer .mp4
  
  Preview
- 8. Other Layers .mp4
  
  Preview
- 9. Training .mp4
  
  Preview
NLP_C3
- NLP_C3_W1_lecture_nb_01_trax_intro.ipynb
  
  Preview
- NLP_C3_W1_lecture_nb_02_classes.ipynb
  
  Preview
- NLP_C3_W1_lecture_nb_03_data_generatos.ipynb
  
  Preview
Week2
- 1. Traditional Language models.mp4
  
  Preview
- 2. Recurrent Neural Networks .mp4
  
  Preview
- 3. Applications of RNNs .mp4
  
  Preview
- 4. Math in Simple RNNs.mp4
  
  Preview
- 5. Cost Function for RNNs .mp4
  
  Preview
- 6. Implementation Note.mp4
  
  Preview
- 7. Gated Recurrent Units.mp4
  
  Preview
- 8. Deep and Bi-directional RNNs.mp4
  
  Preview
C3_W2
- C3_W2_lecture_notebook_GRU.ipynb
  
  Preview
- C3_W2_Lecture_Notebook_Hidden_State_Activation.ipynb
  
  Preview
- C3_W2_lecture_notebook_perplexity.ipynb
  
  Preview
- C3_W2_lecture_notebook_RNNs.ipynb
  
  Preview
- GRU.PNG
  
  Preview
- predictions.npy
  
  Preview
- RNN.PNG
  
  Preview
- targets.npy
  
  Preview
- vanilla_rnn.PNG
  
  Preview
C3_W2_Assignment
- C3_W2_Assignment.ipynb
  
  Preview
model
- model.pkl.gz
  
  Preview
- model.pkl.gz
  
  Preview
- model.png
  
  Preview
- ngrams.png
  
  Preview
- shakespeare.png
  
  Preview
- Untitled.ipynb
  
  Preview
- utils.py
  
  Preview
Week3
- 1. RNNs and Vanishing Gradients .mp4
  
  Preview
- 2. Introduction to LSTMs .mp4
  
  Preview
- 3. LSTM Architecture .mp4
  
  Preview
- 4. Introduction to Named Entity Recognition .mp4
  
  Preview
- 5. Training NERs- Data Processing.mp4
  
  Preview
- 6. Computing Accuracy .mp4
  
  Preview
C3_W3
- C3_W3_Lecture_Notebook_Vanishing_Gradients.ipynb
  
  Preview
- sigmoid_tangent.png
  
  Preview
eval
- events.out.tfevents.1580937148.404e5bd8054c
  
  Preview
- events.out.tfevents.1580949966.e5061a0c8788
  
  Preview
- events.out.tfevents.1581285083.62121f691302
  
  Preview
- events.out.tfevents.1581306901.24f5cdd7b98f
  
  Preview
- events.out.tfevents.1585288908.2feaab97a698
  
  Preview
large
- dataset_params.json
  
  Preview
small
- dataset_params.json
  
  Preview
train
- events.out.tfevents.1580937110.404e5bd8054c
  
  Preview
- events.out.tfevents.1580949955.e5061a0c8788
  
  Preview
- events.out.tfevents.1581285072.62121f691302
  
  Preview
- events.out.tfevents.1581306890.24f5cdd7b98f
  
  Preview
- events.out.tfevents.1585288887.2feaab97a698
  
  Preview
model
- model.pkl.gz
  
  Preview
- model.pkl.gz
  
  Preview
- ner_dataset.csv
  
  Preview
- ner.png
  
  Preview
- ner1.png
  
  Preview
- ner2.png
  
  Preview
- Untitled.ipynb
  
  Preview
- utils.py
  
  Preview
Reading
- 1. (Optional) Intro to optimization in deep learning_ Gradient Descent.pdf
  
  Preview
- 2. (Optional) Understanding LSTMs.pdf
  
  Preview
- 3. Long Short-Term Memory (Deep Learning Specialization C5).pdf
  
  Preview
Week4
- 1. Siamese Networks.mp4
  
  Preview
- 2. Architecture.mp4
  
  Preview
- 3. Cost Function.mp4
  
  Preview
- 4. Triplets.mp4
  
  Preview
- 5. Computing The Cost I.mp4
  
  Preview
- 6. Computing The Cost II .mp4
  
  Preview
- 7. One Shot Learning .mp4
  
  Preview
- 8. Training _ Testing .mp4
  
  Preview
C3_W4
- C3_W4_lecture_notebook_accuracy.ipynb
  
  Preview
- C3_W4_Lecture_Notebook_Modified_Triplet_Loss.ipynb
  
  Preview
- C3_W4_lecture_notebook_siamese.ipynb
  
  Preview
- q1.npy
  
  Preview
- q2.npy
  
  Preview
- ss_matrix.png
  
  Preview
- v1.npy
  
  Preview
- v1v2_stacked.png
  
  Preview
- v2.npy
  
  Preview
- y_test.npy
  
  Preview
C3_W4_Assignment
- C3_W4_Assignment.ipynb
  
  Preview
- C3_W4_triploss1.png
  
  Preview
- C3_W4_triploss2.png
  
  Preview
- meme.png
  
  Preview
model
- model.pkl.gz
  
  Preview
- model.pkl.gz
  
  Preview
wordnet
- adj.exc
  
  Preview
- adv.exc
  
  Preview
- citation.bib
  
  Preview
- cntlist.rev
  
  Preview
- data.adj
  
  Preview
- data.adv
  
  Preview
- data.verb
  
  Preview
- index.adj
  
  Preview
- index.adv
  
  Preview
- index.noun
  
  Preview
- index.sense
  
  Preview
- index.verb
  
  Preview
- lexnames
  
  Preview
- LICENSE
  
  Preview
- noun.exc
  
  Preview
- README
  
  Preview
- verb.exc
  
  Preview
universal_tagset
- ar-padt.map
  
  Preview
- bg-btb.map
  
  Preview
- ca-cat3lb.map
  
  Preview
- cs-pdt.map
  
  Preview
- da-ddt.map
  
  Preview
- de-negra.map
  
  Preview
- de-tiger.map
  
  Preview
- el-gdt.map
  
  Preview
- en-brown.map
  
  Preview
- en-ptb.map
  
  Preview
- en-tweet.map
  
  Preview
- en-tweet.README
  
  Preview
- es-cast3lb.map
  
  Preview
- es-eagles.map
  
  Preview
- es-iula.map
  
  Preview
- es-treetagger.map
  
  Preview
- eu-eus3lb.map
  
  Preview
- fi-tdt.map
  
  Preview
- fr-paris.map
  
  Preview
- hu-szeged.map
  
  Preview
- it-isst.map
  
  Preview
- iw-mila.map
  
  Preview
- ja-kyoto.map
  
  Preview
- ja-verbmobil.map
  
  Preview
- ko-sejong.map
  
  Preview
- nl-alpino.map
  
  Preview
- pl-ipipan.map
  
  Preview
- pt-bosque.map
  
  Preview
- README
  
  Preview
- ru-rnc.map
  
  Preview
- sl-sdt.map
  
  Preview
- sv-talbanken.map
  
  Preview
- tu-metusbanci.map
  
  Preview
- universal_tags.py
  
  Preview
- zh-ctb6.map
  
  Preview
- zh-sinica.map
  
  Preview
punkt
- czech.pickle
  
  Preview
- danish.pickle
  
  Preview
- dutch.pickle
  
  Preview
- english.pickle
  
  Preview
- estonian.pickle
  
  Preview
- finnish.pickle
  
  Preview
- french.pickle
  
  Preview
- german.pickle
  
  Preview
- greek.pickle
  
  Preview
- italian.pickle
  
  Preview
- norwegian.pickle
  
  Preview
- polish.pickle
  
  Preview
- portuguese.pickle
  
  Preview
PY3
- czech.pickle
  
  Preview
- danish.pickle
  
  Preview
- dutch.pickle
  
  Preview
- english.pickle
  
  Preview
- estonian.pickle
  
  Preview
- finnish.pickle
  
  Preview
- french.pickle
  
  Preview
- german.pickle
  
  Preview
- greek.pickle
  
  Preview
- italian.pickle
  
  Preview
- norwegian.pickle
  
  Preview
- polish.pickle
  
  Preview
- portuguese.pickle
  
  Preview
- README
  
  Preview
- russian.pickle
  
  Preview
- slovene.pickle
  
  Preview
- spanish.pickle
  
  Preview
- swedish.pickle
  
  Preview
- turkish.pickle
  
  Preview
- README
  
  Preview
- russian.pickle
  
  Preview
- slovene.pickle
  
  Preview
- spanish.pickle
  
  Preview
- swedish.pickle
  
  Preview
- turkish.pickle
  
  Preview
- punkt.zip
  
  Preview
- questions.csv
  
  Preview
- siamese.png
  
  Preview
4. NLP with Attention Models
- W3.pptx
  
  Preview
Week1
- 1. Course 4 Introduction.mp4
  
  Preview
- 2. Seq2seq.mp4
  
  Preview
- 3. Alignment.mp4
  
  Preview
- 4. Alignment.mp4
  
  Preview
- 5. Setup for Machine Translation.mp4
  
  Preview
- 6. Training an NMT with Attention.mp4
  
  Preview
- 7. Evaluation for Machine Translation.mp4
  
  Preview
- 8. Sampling and Decoding.mp4
  
  Preview
C4_W1
- C4_W1_Ungraded_Lab_Bleu_Score.ipynb
  
  Preview
- C4_W1_Ungraded_Lab_Stack_Semantics.ipynb
  
  Preview
- residual_example_add.png
  
  Preview
- residual_example_multiply.png
  
  Preview
- Stack1.png
  
  Preview
- Stack2.png
  
  Preview
- Stack3.png
  
  Preview
- Stack4.png
  
  Preview
data
- ende_32k.subword
  
  Preview
0.1.0
- dataset_info.json
  
  Preview
- opus-train.tfrecord-00000-of-00002
  
  Preview
- opus-train.tfrecord-00001-of-00002
  
  Preview
- input_encoder.png
  
  Preview
- NMTModel.png
  
  Preview
- plain_rnn.png
  
  Preview
- pre_attention_decoder.png
  
  Preview
- w1_unittest.py
  
  Preview
Reading
- 1. Background on seq2seq.pdf
  
  Preview
- 2. (Optional)_ The Real Meaning of Ich Bin ein Berliner.pdf
  
  Preview
- 3. Attention.pdf
  
  Preview
- 4. Training an NMT with Attention.pdf
  
  Preview
- 5. (Optional) What is Teacher Forcing_.pdf
  
  Preview
- 6. Evaluation for Machine Translation.pdf
  
  Preview
- 7. Sampling and Decoding.pdf
  
  Preview
- 8. References.pdf
  
  Preview
Week2
- 1. Transformers vs RNNs.mp4
  
  Preview
- 2. Transformer Applications.mp4
  
  Preview
- 3. Dot-Product Attention .mp4
  
  Preview
- 4. Causal Attention.mp4
  
  Preview
- 5. Multi-head Attention.mp4
  
  Preview
- 6. Transformer Decoder .mp4
  
  Preview
- 7. Transformer Summarizer .mp4
  
  Preview
attention_lnb_figs
- C4_W2_L3_dot-product-attention_S01_introducing-attention_stripped.png
  
  Preview
- C4_W2_L3_dot-product-attention_S01_introducing-attention.png
  
  Preview
- C4_W2_L3_dot-product-attention_S02_queries-keys-and-values_stripped.png
  
  Preview
- C4_W2_L3_dot-product-attention_S02_queries-keys-and-values.png
  
  Preview
- C4_W2_L3_dot-product-attention_S03_concept-of-attention_stripped.png
  
  Preview
- C4_W2_L3_dot-product-attention_S03_concept-of-attention.png
  
  Preview
- C4_W2_L3_dot-product-attention_S04_attention-math_stripped.png
  
  Preview
- C4_W2_L3_dot-product-attention_S04_attention-math.png
  
  Preview
- C4_W2_L3_dot-product-attention_S05_attention-formula_stripped.png
  
  Preview
- C4_W2_L3_dot-product-attention_S05_attention-formula.png
  
  Preview
- C4_W2_L4_causal-attention_S01_three-ways-of-attention.png
  
  Preview
- C4_W2_L4_causal-attention_S02_causal-attention_stripped.png
  
  Preview
- C4_W2_L4_causal-attention_S02_causal-attention.png
  
  Preview
- C4_W2_L4_causal-attention_S03_causal-attention-math_stripped.png
  
  Preview
- C4_W2_L4_causal-attention_S03_causal-attention-math.png
  
  Preview
- C4_W2_L4_causal-attention_S04_causal-attention-math-2_stripped.png
  
  Preview
- C4_W2_L4_causal-attention_S04_causal-attention-math-2.png
  
  Preview
- C4_W2_L5_multi-head-attention_S01_multi-head-attention_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S01_multi-head-attention.png
  
  Preview
- C4_W2_L5_multi-head-attention_S02_multi-head-attention-2.png
  
  Preview
- C4_W2_L5_multi-head-attention_S03_multi-head-attention-3.png
  
  Preview
- C4_W2_L5_multi-head-attention_S03_multi-head-attention-math_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S04_multi-head-attention-overview_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S04_multi-head-attention-overview.png
  
  Preview
- C4_W2_L5_multi-head-attention_S05_multi-head-attention-concatenation_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S05_multi-head-attention-concatenation.png
  
  Preview
- C4_W2_L5_multi-head-attention_S06_multi-head-attention-scaled-dot-product_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S06_multi-head-attention-scaled-dot-product.png
  
  Preview
- C4_W2_L5_multi-head-attention_S07_multi-head-attention-formula_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S07_multi-head-attention-formula.png
  
  Preview
SVG
- C4_W2_L3_dot-product-attention_S01_introducing-attention.svg
  
  Preview
- C4_W2_L3_dot-product-attention_S02_queries-keys-and-values.svg
  
  Preview
- C4_W2_L3_dot-product-attention_S03_concept-of-attention.svg
  
  Preview
- C4_W2_L3_dot-product-attention_S04_attention-math.svg
  
  Preview
- C4_W2_L3_dot-product-attention_S05_attention-formula.svg
  
  Preview
- C4_W2_L4_causal-attention_S01_three-ways-of-attention.svg
  
  Preview
- C4_W2_L4_causal-attention_S02_causal-attention.svg
  
  Preview
- C4_W2_L4_causal-attention_S03_causal-attention-math.svg
  
  Preview
- C4_W2_L4_causal-attention_S04_causal-attention-math-2.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S01_multi-head-attention.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S02_multi-head-attention-2.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S03_multi-head-attention-3.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S04_multi-head-attention-overview.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S05_multi-head-attention-concatenation.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S06_multi-head-attention-scaled-dot-product.svg
  
  Preview
- C4_W2_L5_multi-head-attention_S07_multi-head-attention-formula.svg
  
  Preview
- C4_W2_lecture_notebook_Attention.ipynb
  
  Preview
- C4_W2_lecture_notebook_Transformer_Decoder.ipynb
  
  Preview
data
- summarize32k.subword.subwords
  
  Preview
1.2.0
- dataset_info.json
  
  Preview
- wikihow-test.tfrecord-00000-of-00001
  
  Preview
- wikihow-train.tfrecord-00000-of-00004
  
  Preview
- wikihow-train.tfrecord-00001-of-00004
  
  Preview
- wikihow-train.tfrecord-00002-of-00004
  
  Preview
- wikihow-train.tfrecord-00003-of-00004
  
  Preview
- wikihow-validation.tfrecord-00000-of-00001
  
  Preview
transformer_decoder_lnb_figs
- C4_W2_L5_multi-head-attention_S05_multi-head-attention-concatenation_stripped.png
  
  Preview
- C4_W2_L5_multi-head-attention_S05_multi-head-attention-concatenation.png
  
  Preview
- C4_W2_L6_transformer-decoder_S01_transformer-decoder.png
  
  Preview
- use-of-tl-Branch-in-tl-CausalAttention.png
  
  Preview
C4_W2_Assignment
- C4_W2_Assignment.ipynb
  
  Preview
- causal.png
  
  Preview
3.0.0
- cnn_dailymail-test.tfrecord-00000-of-00001
  
  Preview
- cnn_dailymail-train.tfrecord-00005-of-00016
  
  Preview
- cnn_dailymail-train.tfrecord-00007-of-00016
  
  Preview
- cnn_dailymail-train.tfrecord-00008-of-00016
  
  Preview
- cnn_dailymail-train.tfrecord-00014-of-00016
  
  Preview
- cnn_dailymail-validation.tfrecord-00000-of-00001
  
  Preview
- dataset_info.json
  
  Preview
- decoder.png
  
  Preview
- dotproduct.png
  
  Preview
- masked-attention.png
  
  Preview
- model.pkl.gz
  
  Preview
- transformer_decoder_1.png
  
  Preview
- transformer_decoder_zoomin.png
  
  Preview
- transformer_decoder.png
  
  Preview
- transformer.png
  
  Preview
- transformerNews.png
  
  Preview
- Untitled.ipynb
  
  Preview
vocab_dir
- summarize32k.subword.subwords
  
  Preview
Reading
- 1. Transformer Applications.pdf
  
  Preview
- 2. Dot-Product Attention.pdf
  
  Preview
- 3. Causal Attention.pdf
  
  Preview
- 4. Multi-head Attention.pdf
  
  Preview
- 5. Transformer Decoder.pdf
  
  Preview
- 6. Transformer Summarizer.pdf
  
  Preview
- 7. References.pdf
  
  Preview
Week3
- 1. Week 3 Overview.mp4
  
  Preview
- 2. Transfer Learning in NLP .mp4
  
  Preview
- 3. ELMo, GPT, BERT, T5 .mp4
  
  Preview
- 4. Bidirectional Encoder Representations from Transformers (BERT) .mp4
  
  Preview
- 5. BERT Objective .mp4
  
  Preview
- 6. Fine tuning BERT .mp4
  
  Preview
- 7. Transformer- T5 .mp4
  
  Preview
- 8. Multi-Task Training Strategy .mp4
  
  Preview
- 9. GLUE Benchmark .mp4
  
  Preview
- 10. Question Answering .mp4
  
  Preview
C4_W3_Assignment
- C4_W3_Assignment_Ungraded_BERT_Loss.ipynb
  
  Preview
- C4_W3_Assignment_Ungraded_T5.ipynb
  
  Preview
- C4_W3_Assignment.ipynb
  
  Preview
- colab_help_1.png
  
  Preview
- colab_help_2.png
  
  Preview
1.0.0
- dataset_info.json
  
  Preview
- squad-validation.tfrecord-00000-of-00001
  
  Preview
- encoder.png
  
  Preview
- fulltransformer.png
  
  Preview
- loss.png
  
  Preview
- qa.png
  
  Preview
- README.md
  
  Preview
- sentencepiece.model
  
  Preview
- test.out
  
  Preview
C4W3
- C4_W3_SentencePiece_and_BPE.ipynb
  
  Preview
- example_bpe.model
  
  Preview
- example_bpe.vocab
  
  Preview
- sentencepiece.model
  
  Preview
Reading
- 1. Week 3 Overview.pdf
  
  Preview
- 2. Transfer Learning in NLP.pdf
  
  Preview
- 3. ELMo, GPT, BERT, T5.pdf
  
  Preview
- 4. Bidirectional Encoder Representations from Transformers (BERT).pdf
  
  Preview
- 5. BERT Objective.pdf
  
  Preview
- 6. Fine tuning BERT.pdf
  
  Preview
- 7. Transformer T5.pdf
  
  Preview
- 8. Multi-Task Training Strategy.pdf
  
  Preview
- 9. GLUE Benchmark.pdf
  
  Preview
- 10. Question Answering.pdf
  
  Preview
- 11. References.pdf
  
  Preview
Week4
- 1. Tasks with Long Sequences.mp4
  
  Preview
- 2. Transformer Complexity.mp4
  
  Preview
- 3. LSH Attention.mp4
  
  Preview
- 4. Motivation for Reversible Layers- Memory! .mp4
  
  Preview
- 5. Reversible Residual Layers .mp4
  
  Preview
- 6. Reformer .mp4
  
  Preview
- Andrew Ng with Quoc Le.mp4
  
  Preview
data
- .README.swp
  
  Preview
- attraction_db.json
  
  Preview
- data.json
  
  Preview
- hospital_db.json
  
  Preview
- hotel_db.json
  
  Preview
- ontology.json
  
  Preview
- police_db.json
  
  Preview
- README
  
  Preview
- restaurant_db.json
  
  Preview
- slot_descriptions.json
  
  Preview
- system_acts.json
  
  Preview
- taxi_db.json
  
  Preview
- tokenization.md
  
  Preview
- train_db.json
  
  Preview
vocabs
- en_8k.subword
  
  Preview
- en_32k.sentencepiece
  
  Preview
- en_32k.sentencepiece.vocab
  
  Preview
- en_32k.subword
  
  Preview
- Reformer.jpg
  
  Preview
- reversible2.PNG
  
  Preview
- ReversibleDecoder.png
  
  Preview
- w4_unittest.py
  
  Preview
- weights
  
  Preview
C4W4
- branch1.PNG
  
  Preview
- branch2.PNG
  
  Preview
- branch3.PNG
  
  Preview
- C4_W4_Ungraded_Lab_Reformer_LSH.ipynb
  
  Preview
- C4_W4_Ungraded_Lab_Revnet.ipynb
  
  Preview
- C4W4_LN2_image1.PNG
  
  Preview
- C4W4_LN2_image2.PNG
  
  Preview
- C4W4_LN2_image3.PNG
  
  Preview
- C4W4_LN2_image4.PNG
  
  Preview
- C4W4_LN2_image5.PNG
  
  Preview
- C4W4_LN2_image6.PNG
  
  Preview
- C4W4_LN2_image7.PNG
  
  Preview
- C4W4_LN2_image8.PNG
  
  Preview
- C4W4_LN2_image9.PNG
  
  Preview
- C4W4_LN2_image10.PNG
  
  Preview
- C4W4_LN2_image11.PNG
  
  Preview
- C4W4_LN2_image12.PNG
  
  Preview
- C4W4_LN2_image13.PNG
  
  Preview
- Reversible2.PNG
  
  Preview
- Revnet1.PNG
  
  Preview
- Revnet2.PNG
  
  Preview
- Revnet3.PNG
  
  Preview
- Revnet4.PNG
  
  Preview
- Revnet5.PNG
  
  Preview
- Revnet6.PNG
  
  Preview
- Revnet7.PNG
  
  Preview
- Revnet8.PNG
  
  Preview
Reading
- 1. Tasks with Long Sequences.pdf
  
  Preview
- 2. Optional AI Storytelling.pdf
  
  Preview
- 3. Transformer Complexity.pdf
  
  Preview
- 4. LSH Attention.pdf
  
  Preview
- 5. Optional KNN _ LSH Review.pdf
  
  Preview
- 6. Motivation for Reversible Layers_ Memory!.pdf
  
  Preview
- 7. Reversible Residual Layers .pdf
  
  Preview
- 8. Reformer.pdf
  
  Preview
- 9. Optional Transformers beyond NLP.pdf
  
  Preview
- 10. References.pdf
  
  Preview
- BERT.pdf
  
  Preview