You can find the original print article in Nature here.
Other Meetings in this Series
Intro to Machine Learning Topics
Summary: This paper includes a brief introduction to and history of machine learning as well as breif summaries of topics in the field.
Handwritten Digit Recognition With a Back-Propagation Network
Abstract: We present an application of back-propagation networks to hand-written digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task. The input of the network consists of normalized images of isolated digits. The method has 1% error rate and about a 9% reject rate on zipcode digits provided by the US Postal Service.
Founder of [email protected] Researcher in cognitive science and machine learning. Focusing on intuitive physics and intuitive psychology.