Join Newsletter

How Much Data do you _really_ need for Deep Learning?

YOW! Data 2019

A common assumption is that we need significant amounts of data in order to do deep learning. Many companies wanting to adopt AI find themselves stuck in the “data gathering” phase and as a result delaying the use of AI to gain competitive advantage in their business. But how much data is enough? Can we get by with less?

In this talk we will explore the impact on our results when we use different amounts of data to train a classification model. It is actually possible to get by with much less data than we might expect. We will discuss why this might be so, in which particular areas this applies, and how we can use these ideas to improve how we train, deploy and engage end-users in our models.

Noon van der Silk




Noon has 18+ years experience in various forms of software engineering, application development, and the design and implementation of machine learning + AI systems. Within AI he has a special interest in the field of computer vision and interactive art.

Noon has a research background, obtaining a Masters in Pure Mathematics, with a focus on quantum computing.

Noon is particularly passionate about empowering people through skill development, which he does through the training courses over at the Braneshop.