by laketide | Apr 26, 2019 | Programming, Theory
Robert Luciani & Hao Huang Fairly recently we came across a paper by Li et.al on generating loss surfaces. The plots looked so cool, we immediately wanted to try it ourselves. Unfortunately, the paper’s associated GitHub repo had so much Python code for...
by laketide | Aug 16, 2017 | Programming
Hi everyone! It’s been over a year since I first blogged about Julia and why its mathematical syntax, metaprogramming abilities, and blazing speed make it an awesome language for data scientists. In this post I want to follow up by comparing it directly with R...
by laketide | Jun 18, 2017 | Programming, Theory
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...
by laketide | Mar 1, 2017 | Programming
This is a small example of how to build a MNIST classifier with MXNet and Julia using executors with customized optimizer and accuracy functions. MXNet is a deep learning framework that is very well suited for parallel computations over several GPUs, i.e. it’s a...
by laketide | Apr 16, 2016 | Programming, Technology
If you’re serious about big data and machine learning, you’re already taking advantage of GPU, MIC, and FPGA powered analytics tools. This new breed of software can allow a single workstation to outperform a 100-node compute cluster in tasks like machine...
by laketide | Jan 3, 2016 | Programming
I’ve always had a soft spot for C because of its rawness, its history, and how much time I spent working with it during university. The type system is generous, memory is openly accessible, and parallelism requires forethought. Though I have worked in many other...
