The Right Path To A Career In Data Science, Data Analysis Part 5.

CHAPTER FIVE

TEXT ANALYSIS (NLP)

Stanford NLP (Video Series)

Full course on “traditional” Natural Language Processing, including sentimentanalysis, Naive Bayes models, n-grams, etc.Deep Learning for Natural Language Processing (Course), (Course materials) Thecurrent bleeding edge of Natural Language Processing. You should finish AndrewNg’s machine learning course first. 

The Unreasonable Effectiveness of Recurrent Neural Networks (Tutorial)

Fantastic breakdown of recurrent neural networks, which are special applications ofdeep learning especially successful in natural language processing. 

Recurrent NN in Keras (Tutorial)

Step-by-step tutorial of implementing a recurrent neural network in Python’s keraspackage.15

RECOMMENDATION SYSTEMS

Recommendation engine tutorial (Video Series)

Introduction to collaborative filters using Python. Does a very nice job of explainingthe intuition behind the algorithm.

Recommender Systems (Video Series)

Discussion of the theory and math behind collaborative filters by Andrew Ng. Moremath-heavy, and it’ll be easier to follow if you have some background with LinearAlgebra.

Collaborative Filtering with Python (Tutorial)

Reference tutorial that implements a music recommender system in Python. 

Collaborative Filtering with R (Tutorial)

The same tutorial as the previous one, except in R.16 

TIME SERIES ANALYSIS

Time Series (Course Material)

Lecture slides, homework, and R Code for the Time Series course at Oregon StateUniversity.

The Little Book of R for Time Series (Online Book)

Very practical step-by-step introduction to using R for time series analysis. Includes code and outputs for each step.

Time Series Forecasting with Python (Tutorial)

Tutorial on performing time series visualization, analysis, and forecasting with Python. 

Seasonal ARIMA with Python (Tutorial)

Introduction to ARIMA models in Python. Includes all code. 

Statistical forecasting, Fuqua School of Business (Online Book)

Course notes from the statistical forecasting course taught at the Fuqua School ofBusiness at Duke University.17

DEEP LEARNING

Neural Networks and Deep Learning (Online Book)

Relatively little-known hidden gem, but one of our favorite resources for learningabout neural networks. Explanations are clear and intuitive.

Unsupervised Feature Learning and Deep Learning (Online Book)

Comprehensive online book that covers a wide range of topics in deep learning. 

Tech Talks by Yann LeCun (Videos)

Tech talks by Yann LeCun, one of the “Godfathers” of modern deep learning. 

Neural Networks for Machine Learning (Video Series)

Course taught by Geoff Hinton, one of the other “Godfathers” of modern deeplearning. 

Hacker’s Guide to Neural Networks (Tutorial)

Neural networks and deep learning taught from the perspective of a computerscientist. Heavy on code and light on math.Stanford 231n: Convolutional Neural Networks (Course Notes), (Lecture Videos)Rigorous course on convolutional neural networks for computer vision. 

Deep NN with Tensorflow (Tutorial)

Step-by-step tutorial for building deep neural networks with Google Tensorflow. 

Build Your Own NN in R (Tutorial)

Building a neural network from scratch in R.18

ANOMALY DETECTION

Anomaly Detection (Video Series)

Part of Andrew Ng’s excellent machine learning course. We recommend startinghere.

Practical Machine Learning: A New Look at Anomaly Detection (PDF)

Short (66-page) textbook on anomaly detection. Excellent introduction with intuitiveexplanations.

A Review of Machine Learning based Anomaly Detection Techniques (PDF)

 Shortacademic overview of anomaly detection techniques. Useful to get a lay of the land. 

Novelty and Outlier Detection (Tutorial)

Tutorial using the sklearn library to perform anomaly detection in Python.

Anomaly Detection in R (Tutorial)

Tutorial using the AnomalyDetection package in R.

Leave a Reply

Your email address will not be published. Required fields are marked *