📈 Simple machine learning, learning by simple humans
This repository has been archived on 2023-11-03. You can view files and clone it, but cannot push or open issues or pull requests.
Go to file
2018-12-22 22:28:17 +01:00
bin Binaries will now be under a bin/ folder to let the project root clean 2017-12-17 18:58:38 -05:00
dev_null We actually don't need to specify the encoding for Python 3 programs... 2017-12-23 11:28:01 -05:00
GradientDescent We actually don't need to specify the encoding for Python 3 programs... 2017-12-23 11:28:01 -05:00
LinearRegression Falls back on scalar entities on affineRegression + Minor fixes 2017-12-22 22:03:47 -05:00
Modules/Graphics Changes random engine by C++11's advised one and takes advantage of some 2017-12-17 18:30:53 -05:00
PolynomialRegression Removes meanNormalization for newton and normequ 2017-12-21 14:20:28 +01:00
.gitignore Removes irrelevant information from README, improves .gitignore and... 2017-12-23 10:35:13 -05:00
CONTRIBUTING.md PEP8 is now respected everywhere 🙇 2017-12-23 11:29:58 -05:00
LICENCE Add LICENCE ! 2016-10-31 13:17:04 +01:00
Makefile Removes irrelevant information from README, improves .gitignore and... 2017-12-23 10:35:13 -05:00
README.md Update 'README.md' 2018-12-22 22:28:17 +01:00

MINDLE Is Not a Deep Learning Experimentation

Requirements

For new C++ codes

  • g++ >= 4.9.2 (of course, we won't upload any binaries here)
  • libsfml-dev >= 2.4.1 (for SFML library)
  • libeigen3-dev >= 3.3.2 (for Eigen library)

For old Python codes

  • Python 3.5.2
  • Theano 0.8.2
  • Numpy 1.11.2
  • Matplotlib 1.5.3
  • TensorFlow 0.11.0rc0

Usage (examples)

  1. Clone the repository : git clone https://github.com/HorlogeSkynet/MINDLE.git
  2. Move into the folder : cd MINDLE/
  3. Compile the C++ : make
  4. Run the C++ programs : ./bin/linearRegression.out
  5. Run the Python programs : python3 dev_null/Theano/LinearRegression/linearRegression.py

Notes to read

  1. Some words about the frameworks we used with Python in the past : Theano & TensorFlow gave us a too high-level abstraction for our needs. We couldn't manage to get something to work, and this is not about getting computations on the GPU; that was just impossible, and we nearly destroy our computers many times... Now, we start from scratch with C++. At least, we would understand the errors thrown.

  2. Based on this "tutorial", you'll be able to perform digits classification by getting the return of loadMNIST.py. If you run it, the code will download and read the training examples automatically.