StandardIO
  • Member for 9 months
  • Last seen more than a month ago
Are Genetic Algorithms suitable for a problem with a non-unique optimal solution?
0 votes

Genetic algorithms (GA) have populations where it has an offspring in every generation usually the same quantity than the original population, so, if a child results from two good solutions (parents) ...

View answer
Why do we lose detail of an image as we go deeper into a ConvNet?
1 votes

A convolution layer has a Kernel that is matrix smaller that the image (in many papers 3*3), so this Kernel have learnable values. The kernel is applied pixel by pixel (and dimensions, for color ...

View answer
How to represent "terminate episode" for Knapsack problem with a Pointer Network?
1 votes

You can find information similar to exposed by Neil, but with more theoretical detail, in the book Deep Learning (Goodfellow et al., 2016) in the chapter 10 (Recurrent networks), more specifically in ...

View answer