How to train neural net on a small dataset?

Introduction

Deep learning is the most exciting area of research nowadays. Autonomous cars, machine translators, voice assistants or visual search engines are on nearly everyone’s lips. It is even more interesting since the breakout of these methods started only a couple of years ago. Every day, new cutting-edge solutions come out and the results become more and more impressive.

Why is it happening right now? The recent success of deep learning models can be encapsulated in 3 major points:

Image for post
Image for post
Standard neural net performs millions of operations per iteration.

2. Creation of various datasets consisting of thousands or millions of samples from different domains;

About

mwosinski

Deep Learning enthusiast. ML Researcher at Yosh.ai. LinkedIn: https://www.linkedin.com/in/mateusz-wosi%C5%84ski-936654160/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store