Machine Learning with Snap!-ML-Sprites (new Version)

[emodrow]

Thank you for the flowers.

[kinestheticlearning]

@kinestheticlearning

... the pooling procedure takes from each of the four (they must be four, if I understand correctly) 50 x 50 pixels sized pools:

1. separately R values to compute the 'mean R value' in the pool,
2. separately G values (from the same pool) to compute 'mean G value' in the same pool,
3. separately B values ... ... to compute 'mean B value' in the same pool

@emodrow

That's right.

Okey, then it can be illustrated as follows:

[emodrow]

Great!