Skip to content

view

Dmytro Mishkin
presents
CNNs - from the Basics to Recent Advances.
 
On 2016-10-04 11:00 at G205
 
The presentation will cover the convolution neural network (CNN) design. 
First,
the main building blocks of CNNs will be introduced. Then we systematically
investigate the impact of a range of recent advances in CNN architectures and
learning methods on the object categorization (ILSVRC) problem. In the
evaluation, the influence of the following choices of the architecture are
tested: non-linearity (ReLU, ELU, maxout, compatibility with batch
normalization), pooling variants (stochastic, max, average, mixed), network
width, classifier design (convolution, fully-connected, SPP), image
pre-processing, and of learning parameters: learning rate, batch size,
cleanliness of the data, etc. 
Back to the list