AI~f(ML|knowledge) | Realistic engineer | Intellectual financial decision-making systems / previously intellectual security systems in aviation and astronautics
Kernels is all you need:
"Kernel methods don’t overfit and do generalize well to test data without any need for regularization, similar to neural networks and contrary to what you’d expect from traditional learning theory."
#AI#MachineLearningquantamagazine.org/a-new-lin…
Wasserstein Distance Using C# and Python -- Visual Studio Magazine
It's often preferable to alternative distance functions used to measure the distance between two probability distributions in machine learning projects. #MachineLearningvisualstudiomagazine.com/art…
The inverse, or maybe the logical consequence of, @fchollet's observation: within 10-20 years, there won't be a field called "computer science" (except for a few theoreticians). All the "computer scientists" will be in their respective sciences, or art or business schools.