kuza55The Gradient in Gradient Boosted Trees: How to fit a tree to an arbitrary loss functionI’ve been trying to understand gradient boosted trees on and off for the last few weeks, and it was a surprisingly frustrating exercise…Jul 29, 2017Jul 29, 2017
kuza55Transparent Multi-GPU Training on TensorFlow with KerasKeras should be getting a transparent data-parallel multi-GPU training capability pretty soon now, but in the meantime I thought I would…Oct 8, 201614Oct 8, 201614
kuza55Deep Learning in the Cloud: TensorFlow on EC2 Spot Instances with AnsibleIf you’ve ever tried playing with Deep Learning, you’ll have found out that you’re not going to get very far without a GPU, and if you…Jul 12, 20162Jul 12, 20162
kuza55Password Sage BetaEarly this year, I tried to brainstorm ways to defeat phishing, and recall asking myself why no-one was doing something like Password Alert…Nov 30, 20151Nov 30, 20151