Viewing profile — pkoperek

To be honest I think this may be actually an advantage: it explains concepts which otherwise are just weird parameters in code. Since it is pretty lengthy I would actually recommen…

Good read. Does anyone know if any of the experimentation frameworks actually uses these methods to make the results more reliable (e.g. allow to automatically apply winsorization …

Evolving neural networks with use of the fitness predictors (co-evolution). The project has stalled a bit due to lack of time (family etc) but overall I want to get back hacking ar…

There is one angle I really like in this concept: letting go and acknowledging that something is imperfect rather than continuing to try to make it ideal. I saw so many times peopl…

Genuinely interested - could you share some good resources about it?

Apart from NEAT/HyperNEAT there are also other approaches to neuroevolution (I think in this context it is referred to as "Evolutionary Neural Architecture Search" [0]). Evolution …

I think the point is that the control group and treatment groups are in fact the same group (you were giving them the same "service" before starting the experiment) and any differe…