Strong AI & Existential Risks

There has been a recrudescence of hysterical talks about Strong Artificial Intelligence (AI) lately. Strong AI is artificial intelligence matching and eventually going beyond the full human cognitive capacity.  Weak AI, by opposition, is the replication of some facets of human cognition:  face recognition, voice recognition, pattern matching, etc.  . The ultimate goal of AI is to … More Strong AI & Existential Risks

Azure ML – Over fitting with Neural Networks

In a past post, I discussed the concept of over fitting in Machine Learning.  I also alluded to it in my post about Polynomial Regression. Basically, over fitting occurs when your model performs well on training data and poorly on data it hasn’t seen. In here I’ll give an example using Artificial Neural Networks.  Those … More Azure ML – Over fitting with Neural Networks

AzureML – Polynomial Regression with SQL Transformation

I meant to illustrate over fitting (discussed in a past blog) with AzureML.  An easy way to illustrate it is to fit a bunch of sample points near perfectly and the best tool for that is Polynomial Regression. I was surprised to see that AzureML doesn’t support Polynomial Regression natively.  But…  while thinking about it, … More AzureML – Polynomial Regression with SQL Transformation