Natural Language Processing

Welcome to the Natural Language Processing Nanodegree program!

You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.

Arpan will give you an overview of how to build a Natural Language Processing pipeline.

Learn to prepare text obtained from different sources for further processing, by cleaning, normalizing and splitting it into individual words or tokens.

In this section, you'll learn how to build a spam email classifier using the naive Bayes algorithm.

Learn Hidden Markov Models, and apply them to part-of-speech tagging, a very popular problem in Natural Language Processing.

Learn how to build a simple question-answering agent using IBM Watson.

An introduction of the course outline and prerequisite.

Transform text using methods like Bag-of-Words, TF-IDF, Word2Vec and GloVE to extract features that you can use in machine learning models.

In this section, you'll learn to split a collection of documents into topics using Latent Dirichlet Analysis (LDA). In the lab, you'll be able to apply this model to a dataset of news articles.

Learn about using several machine learning classifiers, including Recurrent Neural Networks, to predict the sentiment in text. Apply this to a dataset of movie reviews.

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!

Attention is one of the most important recent innovations in deep learning. In this section, you'll learn attention, and you'll go over a basic implementation of it in the lab.

This section will prepare you for the Machine Translation project. Here you will get hands-on practice with RNNs in Keras.

Introduce the course outline and the course prerequisite

Get acquainted with the principles and applications of VUI, and get introduced to Alexa skills.

Build your own Alexa skill and deploy it!

Learn how an automatic speech recognition (ASR) pipeline works.

Ortal will introduce Recurrent Neural Networks (RNNs), which are machine learning models that are able to recognize and act on sequences of inputs.

Luis explains Long Short-Term Memory Networks (LSTM), and similar architectures which have the benefits of preserving long term memory.

Learn about a number of different hyperparameters that are used in defining and training deep learning models. We'll discuss starting values and intuitions for tuning each hyperparameter.

In this section you'll get a hands-on introduction to Keras. You'll learn to apply it to analyze movie reviews.

Implement a sentiment prediction RNN

In this section you'll get a hands-on introduction to TensorFlow, Google's deep learning framework, and you'll be able to apply it on an image dataset.

In this lesson, you'll learn about embeddings in neural networks by implementing the word2vec model.

Learn how to use PyTorch to build and train deep neural networks. By the end of this lesson, you will build a network that can classify images of dogs and cats with state-of-the-art performance.

In this lesson, you'll learn about embeddings in neural networks by implementing the Word2Vec model.

Learn how to represent memory in code. Then define and train RNNs in PyTorch and apply them to tasks that involve sequential data.

In this lesson, we'll walk through a tutorial showing how to deploy PyTorch models with Torch Script.