Custom networks in MXNet on Julia – part 2

Hi, Albin here again! Part of the work I do at LakeTide is making our machine learning models more computationally efficient. For instance, sometimes the neural networks we develop end up being big enough that they don’t fit on GPUs anymore. Other times we just...

Why Deep Learning?

Your competitors are probably not using it yet. Software from well-established analytics vendors has always been 5 to 10 years behind leading machine learning technology. Consider the following example: 2001 – The Random Forest algorithm was formalized by Leo...