Participants in this training typically have a background in a quantitative subject, analytics or are junior/medior data scientists. Additionally, they should have the ambition to dive deeper into specific machine learning algorithms and language-based techniques.
In order to get most value out of the training, you have basic experience with machine learning in Python. You should have knowledge about the machine learning workflow and familiarity with concepts such as overfitting/underfitting, scoring metrics and parameter tuning. If you previously followed the Basic Machine Learning training these prerequisites are satisfied.
After the training you receive a Certificate of Completion.
This NLP specialization consists of 1 full day of theory and training. This training is given in our offices on specific dates. We can also tailor the training and dates if you have specific needs.
We start off by giving a broad introduction on NLP and its potential applications, before describing the most important preprocessing and feature extraction techniques, such as tokenization, stemming, N-grams, tf-idf and Part Of Speech tagging. This gives us a good foundation before discussing several common models for NLP that incorporate relationships between words, such as Bayesian Models and Word Embeddings.
The training includes theory, demos, and hands-on exercises. After this training you will have gained knowledge about:
After the training you receive a Certificate of Completion.