Ressourcen Machine Learning und Text Mining

Python


Pandas
Feature rich implementation of Data Frames in Python. Basis for most data wrangling activities.
Library

Python for Data Analysis
Book about the details for Pandas by McKinney.

Machine Learning


Machine Learning Coursera Course
Solid introductory course by Andrew Ng. Basically no knowledge except high school math required.
Online Course

Sci Kit Learn Tutorial
Tutorial for various machine learning algorithms using the popular Python library.
Library

Hands-On Machine Learning with Scikit-Learn & Tensorflow
Book by Géron.

Text Mining


Natural Language Toolkit
Contains various algorithms and datasets relevant for natural language processing.
Library

Speech and Language Processing
Extensive ressource for natural language processing including the transition to machine learning / neural network models.
Book

Gensim
Performant library for streaming documents and computing topic models or document representations.
Library

Spacy
Library for various text processing purposes including tokenization, named entity recognition, dependency parsing, text classification.
Library


Neural Networks


Fast.ai
Practical introduction to concepts and architectures of neural networks. Ranges from basic materials to quite advanced topics.
Online Course

Keras
High level neural network API running on top of Tensorflow.
Library

Tensorflow
Neural network / Machine Learning library by Google.
Library
Tutorials

A Primer on Neural Network Models for Natural Language Processing
Review paper by Goldberg about Neural Network Models for NLP.
Review Paper

Stanford 224N: Natural Language Processing with Deep Learning
Lecture
Lecture Youtube Playlist

Stanford 231N: Convolutional Neural Networks
Lecture
Lecture Youtube Playlist

Collection of Datasets



Collection of additional Books


Barber 2012 Bayesian Reasoning and Machine Learning Link
Hastie et al. 2009 Elements of Statistical Learning Link
Hastie et al. 2013 Introduction to Statistical Learning Link