课时1：welcome-to-this-course-and-specialization

课时2：who-we-are

课时3：machine-learning-is-changing-the-world

课时4：why-a-case-study-approach

课时5：specialization-overview

课时6：how-we-got-into-ml

课时7：who-is-this-specialization-for

课时8：what-you-ll-be-able-to-do

课时9：the-capstone-and-an-example-intelligent-application

课时10：the-future-of-intelligent-applications

课时11：starting-an-ipython-notebook

课时12：creating-variables-in-python

课时13：conditional-statements-and-loops-in-python

课时14：creating-functions-and-lambdas-in-python

课时15：starting-graphlab-create-loading-an-sframe

课时16：canvas-for-data-visualization

课时17：interacting-with-columns-of-an-sframe

课时18：using-apply-for-data-transformation

课时19：predicting-house-prices-a-case-study-in-regression

课时20：what-is-the-goal-and-how-might-you-naively-address-it

课时21：linear-regression-a-model-based-approach

课时22：adding-higher-order-effects

课时23：evaluating-overfitting-via-training-test-split

课时24：training-test-curves

课时25：adding-other-features

课时26：other-regression-examples

课时27：regression-ml-block-diagram

课时28：loading-exploring-house-sale-data

课时29：splitting-the-data-into-training-and-test-sets

课时30：learning-a-simple-regression-model-to-predict-house-prices-from-house-size

课时31：evaluating-error-rmse-of-the-simple-model

课时32：visualizing-predictions-of-simple-model-with-matplotlib

课时33：inspecting-the-model-coefficients-learned

课时34：exploring-other-features-of-the-data

课时35：learning-a-model-to-predict-house-prices-from-more-features

课时36：applying-learned-models-to-predict-price-of-an-average-house

课时37：applying-learned-models-to-predict-price-of-two-fancy-houses

课时38：analyzing-the-sentiment-of-reviews-a-case-study-in-classification

课时39：what-is-an-intelligent-restaurant-review-system

课时40：examples-of-classification-tasks

课时41：linear-classifiers

课时42：decision-boundaries

课时43：training-and-evaluating-a-classifier

课时44：whats-a-good-accuracy

课时45：false-positives-false-negatives-and-confusion-matrices

课时46：learning-curves

课时47：class-probabilities

课时48：classification-ml-block-diagram

课时49：loading-exploring-product-review-data

课时50：creating-the-word-count-vector

课时51：exploring-the-most-popular-product

课时52：defining-which-reviews-have-positive-or-negative-sentiment

课时53：training-a-sentiment-classifier

课时54：evaluating-a-classifier-the-roc-curve

课时55：applying-model-to-find-most-positive-negative-reviews-for-a-product

课时56：exploring-the-most-positive-negative-aspects-of-a-product

课时57：document-retrieval-a-case-study-in-clustering-and-measuring-similarity

课时58：what-is-the-document-retrieval-task

课时59：word-count-representation-for-measuring-similarity

课时60：prioritizing-important-words-with-tf-idf

课时61：calculating-tf-idf-vectors

课时62：retrieving-similar-documents-using-nearest-neighbor-search

课时63：clustering-documents-task-overview

课时64：clustering-documents-an-unsupervised-learning-task

课时65：k-means-a-clustering-algorithm

课时66：other-examples-of-clustering

课时67：clustering-and-similarity-ml-block-diagram

课时68：loading-exploring-wikipedia-data

课时69：exploring-word-counts

课时70：computing-exploring-tf-idfs

课时71：computing-distances-between-wikipedia-articles

课时72：building-exploring-a-nearest-neighbors-model-for-wikipedia-articles

课时73：examples-of-document-retrieval-in-action

课时74：recommender-systems-overview

课时75：where-we-see-recommender-systems-in-action

课时76：building-a-recommender-system-via-classification

课时77：collaborative-filtering-people-who-bought-this-also-bought

课时78：effect-of-popular-items

课时79：normalizing-co-occurrence-matrices-and-leveraging-purchase-histories

课时80：the-matrix-completion-task

课时81：recommendations-from-known-user-item-features

课时82：predictions-in-matrix-form

课时83：discovering-hidden-structure-by-matrix-factorization

课时84：bringing-it-all-together-featurized-matrix-factorization

课时85：a-performance-metric-for-recommender-systems

课时86：optimal-recommenders

课时87：precision-recall-curves

课时88：recommender-systems-ml-block-diagram

课时89：loading-and-exploring-song-data

课时90：creating-evaluating-a-popularity-based-song-recommender

课时91：creating-evaluating-a-personalized-song-recommender

课时92：searching-for-images-a-case-study-in-deep-learning

课时93：what-is-a-visual-product-recommender

课时94：using-precision-recall-to-compare-recommender-models

课时95：application-of-deep-learning-to-computer-vision

课时96：deep-learning-performance

课时97：demo-of-deep-learning-model-on-imagenet-data

课时98：other-examples-of-deep-learning-in-computer-vision

课时99：challenges-of-deep-learning

课时100：deep-features

课时101：deep-learning-ml-block-diagram

课时102：loading-image-data

课时103：training-evaluating-a-classifier-using-raw-image-pixels

课时104：training-evaluating-a-classifier-using-deep-features

课时105：loading-image-data

课时106：creating-a-nearest-neighbors-model-for-image-retrieval

课时107：querying-the-nearest-neighbors-model-to-retrieve-images

课时108：querying-for-the-most-similar-images-for-car-image

课时109：displaying-other-example-image-retrievals-with-a-python-lambda

课时110：you-ve-made-it

课时111：deploying-an-ml-service

课时112：what-happens-after-deployment

课时113：open-challenges-in-ml

课时114：where-is-ml-going

课时115：whats-ahead-in-the-specialization

课时116：thank-you