Data Preprocessing

From Ufldl

Revision as of 05:43, 29 April 2011 by Jngiam (Talk | contribs)
Jump to: navigation, search

Contents

Overview

Data preprocessing plays a very important in many deep learning algorithms. In practice, many methods work best after the data has been normalized and whitened. However, the exact parameters for data preprocessing are usually not immediately apparent unless one has much experience working with the algorithms. In this page, we hope to demystify some of the preprocessing methods and also provide tips (and a "standard pipeline") for preprocessing data.

Feature Normalization

D

PCA/ZCA Whitening

How to choose epsilon? Do we need low-pass filtering?

Large Images

1/f Whitening


Standard Pipeline

Model Idiosyncrasies

Sparse Autoencoder

Sigmoid Decoders

Linear Decoders

Independent Component Analysis

Personal tools