[UDACITY] NLP Foundations Nanodegree
Master the skills to get computers to understand, process, and manipulate human language. Build models on real data, and get hands-on experience with sentiment analysis, machine translation, and more.
Part 01 : Introduction to Natural Language Processing
Module 01: Intro to NLP
Lesson 01: Intro to Natural Language Processing
Find out how Natural Language Processing is being used in the industry, why it is challenging, and learn to design an NLP solution using IBM Watson’s cloud-based services.
Lesson 02: Bookworm
Learn how to build a simple question-answering agent using IBM Watson.
Part 02 : Introduction to Deep Learning
Module 01: Intro to Deep Learning
Lesson 01: Deep Neural Networks
Luis will give you solid foundations on Deep Learning, and teach you how to apply Neural Networks to analyze real data!
Module 02: Convolutional Neural Networks
Lesson 01: Convolutional Neural Networks
Module 03: TensorFlow
Lesson 01: Intro to TensorFlow
In this section you’ll get a hands-on introduction to deep learning and Tensorflow, Google’s deep learning framework, and you’ll be able to apply it on an image dataset.
Module 04: Intro to Recurrent Networks
Lesson 01: Recurrent Neural Networks
Jeremy explains Recurrent Neural Networks, and their cutting edge applications to text-based sequence generation
Lesson 02: Long Short-Term Memory Networks (LSTM)
Luis explains Long Short-Term Memory Networks (LSTM), and similar architectures which have the benefits of preserving long term memory.
Lesson 03: Implementing RNNs and LSTMs
In this lesson, Mat will review the concepts of RNNs and LSTMs, and then you’ll see how a character-wise recurrent network is implemented in TensorFlow.
Lesson 04: Hyperparameters
In this section, Jay will teach you about some important hyperparameters used for our deep learning work, including those used for Recurrent Neural Networks.
Lesson 05: Sentiment Prediction with RNN
In this lesson you’ll implement a sentiment prediction RNN
Part 03 : NLP Fundamentals
Module 01: NLP Fundamentals
Lesson 01: Natural Language Processing
An overview of how to build an end-to-end Natural Language Processing pipeline.
Lesson 02: Text Processing
Learn to prepare text obtained from different sources for further processing, by cleaning, normalizing and splitting it into individual words or tokens.
Part 04 : Feature Extraction
Module 01: Feature Extraction
Lesson 01: Feature Extraction
Transform text using methods like Bag-of-Words, TF-IDF, Word2Vec and GloVe to extract features that you can use in machine learning models.
Part 05 : Modeling
Module 01: Modeling in NLP
Lesson 01: Modeling
A selection of different NLP tasks and how to build models that accomplish them.
Module 02: Project: Machine Translation
Lesson 01: Machine Translation
Apply the skills you’ve learnt in Natural Language Processing to the challenging and extremely rewarding task of Machine Translation. Bonne chance!
Project Description – Machine Translation
Project Rubric – Machine Translation
Part 06 (Elective): NLP Supplementary
Module 01: NLP: Supplementary
Lesson 01: Embeddings and Word2Vec
In this lesson, you’ll learn about embeddings in neural networks by implementing the word2vec model.
Lesson 02: Sequence to Sequence
Here you’ll learn about a specific architecture of RNNs for generating one sequence from another sequence. These RNNs are useful for chatbots, machine translation, and more!
Size: 1.05 GB