https://github.com/coder-sasha/ml-tutorial
Machine Learning code examples and texts: 2019-2023
https://github.com/coder-sasha/ml-tutorial
cnn lstm ml nltk-python python3 spacy-nlp
Last synced: 27 days ago
JSON representation
Machine Learning code examples and texts: 2019-2023
- Host: GitHub
- URL: https://github.com/coder-sasha/ml-tutorial
- Owner: coder-sasha
- Created: 2025-03-16T00:07:26.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-16T01:19:56.000Z (about 1 year ago)
- Last Synced: 2025-03-16T01:20:41.606Z (about 1 year ago)
- Topics: cnn, lstm, ml, nltk-python, python3, spacy-nlp
- Language: Jupyter Notebook
- Homepage:
- Size: 2.42 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
**Machine Learning (ML) and Artificial Intelligence (AI) have become phrases of the decade.**
The goal of these tutorials is to give you an introduction to the basic concepts and mechanics of creating machine learning systems.
The scripts and notebooks will walk you through working examples of machine learning code so that you can see the blueprint and begin to create your own working machine learning programs.
We will explore decision trees, an approach to machine learning that produces logical rules from data, then turn to neural networks and finally explore a practical application of ML tools and methods.
**What Exactly Is Machine Learning?**
Machine learning is just a different way of computer programming.
In traditional programming, we tell the computer what to do.
In machine learning, instead of giving the computer a program or formulas we describe what output we want,
exemplified an input, and the machine (or rather the program) creates data procesing rules that should give us desired results:
Traditional Programming:
Rules + Data → Output
Machine Learning:
Desired Output + Data → Rules
This mini-tutorial offers Python notebooks scripts. Scripts are run as a regular Python programs, notebooks (file format is .ipynb) are run from your web browser.
The advantage of notebooks over regular Python scripts is that an interactive Python notebook integrates code, documentation, and the result of running the code all in one place.
The recommended sequence of study is:
• begin with **work_with_python** and **work_with_pandas** then follow to **nlp**;
• start to wotk with Neural Networks in **simple_nn**;
• proceed with **text_classification_with_nn**, **nn_for_mktdata**;
• finish by opening **work_with_spacy**;
**Have Fun!**