Deep Learning

5 important questions on Deep Learning

How does a convolutional neural network work?

Every neuron (filter) produced one new image (feature map), these n maps are used as input for the next layer.

What is the formula for the parameters?

Parameters = (filtersizex,y * feature maps input + bias) * feature maps output

What is the formula for feature space dimension?

Feature size dimension = (input size x + 2*padding - filtersize x)/stride +bias
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

How are features extracted in a convolutional way?

- Low model complexity
- Localized
- Translation invariant

What are benefits of CNN?

Model inherent structures in data (in time or space)
No need for feature engineering

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo