This project purpose is to reproduce some of the results in Measuring the Intrinsic Dimension of Objective Landscapes and then:

1. report on their main properties compared to standard smaller neural network
2. test experimentally their performance for different subspace dimensions
3. test experimentally their performance for different families of P

To see the resuts of the experiments look at the commented lines in runs.sh. The data necessary for training will be downloaded automatically with the first run and then read from the filesystem.

A more detailed description of the project is in report.tex.

Stuff from the authors:

• arXiv
• GitHub
• Uber Engineering
• YouTube
• Papers with Code

Stuff from other people:

• VITALab excellent explanation!
• A good set of slides from one of the authors.
• A study using intrinsic dimensionality.
• SlideShare
• A non particularly revealing article

• Scikit-learn
• Very Sparse Random Projections
• Database-friently Random projections

• Fastfood — Approximating Kernel Expansions in Loglinear Time
• Scikit-learn
• Scikit-learn fastfood digits