root
/
Branch-AI
mirror of https://github.com/01-edu/Branch-AI.git
2
0
Fork 2
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
173 Commits
1 Branch
0 Tags
51 MiB
Branch: master
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'master'
${ noResults }
Branch-AI/piscine/week03/day03
eslopfer f6ff4102aa
docs(Branch-AI): Add missing data file 		2 years ago
..
ex00 Renaming with uppercase of readme files to respect standard 2 years ago
ex01 Renaming with uppercase of readme files to respect standard 2 years ago
ex02 docs(Branch-AI): Add missing data file 2 years ago
ex03 Renaming with uppercase of readme files to respect standard 2 years ago
ex04 Renaming with uppercase of readme files to respect standard 2 years ago
ex05 add link to the dataset (#44) 2 years ago
README.md Renaming with uppercase of readme files to respect standard 2 years ago

README.md

W3D03 Piscine AI - Data Science

Keras 2

The goal of this day is to learn to use Keras to build Neural Networks and train them on small data sets. This helps to understand the specifics of networks for classification and regression.

Note:

The audit will provide the code and output because it is not straightforward to reproduce results using Keras. There are many source of randomness. Even if all the seeds are fixed to a constant they may be other source of randomness. https://machinelearningmastery.com/reproducible-results-neural-networks-keras/

Exercises of the day

  • Exercise 1 Regression - Optimize
  • Exercise 2 Regression example
  • Exercise 3 Multi classification - Softmax
  • Exercise 4 Multi classification - Optimize
  • Exercise 5 Multi classification example

Virtual Environment

  • Python 3.x
  • NumPy
  • Jupyter or JupyterLab
  • Keras

Version of Keras I used to do the exercises: 2.4.3. I suggest to use the most recent one.

Ressources