Inspecting neural network internals using generated toy data
HTML Python
Switch branches/tags
Nothing to show
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
report
results
.gitignore
correlations.py
dataset.py
evaluation.py
experiments.py
helpers.py
license.txt
logistic_sgd.py
mlp.py
mlp_theano.py
rbmclass.py
readme.md
stacked_rbms.py
toydata.py
visualisation.py

readme.md

This repo contains the results of a course project I did for my machine learning studies. My idea was to try out generating toy data samples (20-bit vectors), and looking if the features that neural networks (RBM and MLP) would find would match the latent variables that were used to generate the data.

Generate toy data -> Feed data to neural network -> evaluate if neurons found latent variables

Reading the report

The project report is in the form of an IPython Notebook, allowing the reader to rerun the experiments while reading, and to modify them to try out new things.

To read and explore the report, clone the repo and run ipython notebook report/report.ipynb.

You will need:

  • ipython,
  • ipython-notebook
  • the following python modules: (run pip install <module> to install modules)
    • numpy
    • matplotlib
    • sklearn
    • theano (only for MLP experiments)

Alternatively, you can take a read-only version of the report, as html or PDF.