Training schedule
Join waiting listIN-COMPANY TRAINING PROGRAMS
Contact Giovanni Lanzani, if you want to know more about custom data & AI training for your teams. He’ll be happy to help you!
Check out more
Apply Deep Learning to Natural Language Processing (NLP)
Deep Learning is a powerful technique that has revolutionized many industries by dealing with unstructured data in a novel and different way. Textual data is one of these. Discover current state-of-the-art techniques that can help — for example — to determine intent and sentiment in text. This 2-day training offers a deep-dive into game-changer tech!
This training is for you if…
You are eager to apply state-of-the-art language models to your text data problems
You are looking for a practical course that focusses on application
You are comfortable with Python and are familiar with basic data science concepts (train vs. test set, etc.)
Bonus if you have some familiarity with deep learning, though not necessary!
This training is not for you if…
You never work with text data and never expect to
Traditional techniques like word counts suffice for your simple text problems (see data science training?)
You are looking for an introductory course on deep learning (see deep learning training)
You would prefer to apply deep learning to image data (see deep learning for image processing)
Clients we've helped
What you'll learn
- The theory that underlies Deep Learning and learn to apply it to solve Natural Language Processing problems.
- How Deep Learning can be applied to textual data and make yourself comfortable with the Natural Language Processing terminology: embeddings, dimensionality reduction, and more.
- How the Deep Learning approach is fundamentally different than the traditional approach;
- The (practical) pros and cons of working with either approach.
- How to apply transfer learning in NLP and use pretrained Bert models.
The schedule
- Introduction
- Baseline NLP models
- Building deep NLP models
- The encoder-decoder architecture
- Attention mechanism (BERT)
- Transfer learning in NLP (Hugging face)
Benchmark the performance of bag of word models vs. deep learning models on short texts. The participants need to write benchmarking scripts that compare a scikit-learn pipeline against a deep learning model written in Keras. The scikit-learn pipeline will also require the students writing a transformer that accepts Bert/Spacy embeddings to see the benefits of using pretrained models.
learning journey
Data Science Learning Journey
What will you learn during the Deep Learning Applied to NLP
course:
- This course helps you understand what makes Deep Learning so powerful, especially compared to the traditional techniques, when applied to NLP
- You will understand and be able to use Bert models
- We will also teach you how about embeddings, dimensionality reduction, and how to build these using the Keras API.