Although neural networks have been studied for decades, over the past couple of years there have been many small but significant changes in the default techniques used. For example, ReLU (rectified ...

There is a phenomenon in the Python programming language that affects the efficiency of data representation and memory. I call it the "invisible line." This invisible line might seem innocuous at ...

For the past few months, I've been covering different software packages for scientific computations. For my next several articles, I'm going to be focusing on using Python to come up with your own ...

Among the innovations that power the popular open source TensorFlow machine learning platform are automatic differentiation (Autograd) and the XLA (Accelerated Linear Algebra) optimizing compiler for ...

With Python and NumPy getting lots of exposure lately, I'll show how to use those tools to build a simple feed-forward neural network. Over the past few months, the use of the Python programming ...