Study Guide

Objective

You can create conventional natural language processing (NLP) based models
You know the basic structure of natural language processing machine learning applications and their differences to other conventional machine learning applications
You can create suitable error metrics for your natural language processing based machine learning models
You can pre-process data into suitable formats regarding natural language processing based machine learning training code

Content

Basics of NLP: vectorization, tokenization and word embeddings
Classic machine learning and deep learning in NLP
Common NLP applications
NLP data preprocessing and optimization methods
Basics of LLM (Large language models)

Qualifications

Basics of programming, Basics of Deep Learning, Basics of conventional machine learning methods, Basics of Python data analytics modules/libraries

Assessment criteria, satisfactory (1)

You are aware of the common use cases of natural language processing in machine learning
You can create simple text-based AIs by using conventional machine learning tools
You can create basic error metrics for a text-based AI

Assessment criteria, good (3)

You have experience with common use cases of natural language processing in machine learning
You can create various text-based AIs by using conventional machine learning tools
You can create basic error metrics for a text-based AI
You can optimize your text data and selected algorithms when training a text-based AI

Assessment criteria, excellent (5)

You have experience with common use cases of natural language processing in machine learning
You can create various text-based AIs by using conventional machine learning tools
You can create various error metrics for a text-based AI
You can optimize your text data and selected algorithms when training a text-based AI
You can combine your text-based AI models into other models and systems effectively