Category Archives: Regression

Multivariate Regression with Neural Networks. Training to Shoot

Machine learning is alchemy – researchers in artificial intelligence at Google have recently proclaimed. Any high school or college student that has ever tried to solve nonlinear systems of equations with gradient descent method knows that already, kind of… Even for a perfect bowl-shaped cost-surface, gradient descent method will converge… Read more »

Multivariate Regression with Neural Networks: Unique, Exact and Generic Models

Michael Nielsen provides a visual demonstration in his web book Neural Networks and Deep Learning that a 1-layer deep neural network can match any function . It is just a matter of the number of neurons to get a prediction that is arbitrarily close – the more the neurons the better the approximation…. Read more »