pith. sign in

arxiv: 1507.05053 · v1 · pith:I57ETKO3new · submitted 2015-07-17 · 💻 cs.CV · cs.LG· cs.NE

Massively Deep Artificial Neural Networks for Handwritten Digit Recognition

classification 💻 cs.CV cs.LGcs.NE
keywords handwrittenrateachieveartificialboltzmanncardconsistingdatabase
0
0 comments X
read the original abstract

Greedy Restrictive Boltzmann Machines yield an fairly low 0.72% error rate on the famous MNIST database of handwritten digits. All that was required to achieve this result was a high number of hidden layers consisting of many neurons, and a graphics card to greatly speed up the rate of learning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.