Hacker News Reader

hoaphumanoidon Examples and best practices for building recommendation systems

thanks for the comment, would this definition be clearer: "Recall at k is the proportion of relevant items found in the top-k recommendations"?

hoaphumanoidon Examples and best practices for building recommendation systems

hey one of the authors here. We are planning to create some notebooks on recommendation about recommendation algos :-)

hoaphumanoidon When to Use Transfer Learning: Experimentation on Different Datasets in PyTorch

Sometimes the notebook doesn't render, here there is a different option: https://nbviewer.jupyter.org/github/miguelgfierro/sciblog_su...

hoaphumanoidon Microsoft releases revamped Azure ML, new AI tools

Miguel Fierro from Microsoft here: Joseph Sirosh session will be broadcasted live at 2.15pm ET in this link: https://myignite.microsoft.com/sessions/56555?source=session...

hoaphumanoidon Lessons Learned from Benchmarking Fast Machine Learning Algorithms

Yes, it was initially forked from an internal boosted trees library from Microsoft. The guys who created it are Microsoft Research Asia

hoaphumanoidon Lessons Learned from Benchmarking Fast Machine Learning Algorithms

The LightGBM implementation on GPU is based on this paper: https://arxiv.org/abs/1706.08359 they use several smart techniques to make the computation faster. One is how they create histograms of features that are computed in parallel in the GPU

hoaphumanoidon Lessons Learned from Benchmarking Fast Machine Learning Algorithms

In deep learning, the algorithm that is used, back propagation, is basically a chained matrix multiplication, which is good for the GPU structure. However, for boosted trees the optimization problem is a little bit different, there is a sorting and then a computation of a gradient and hessian. In this case, it is not as efficient for GPU than deep learning.

hoaphumanoidon How to deploy a Deep Learning API for image classification

The design of the blog is open source, here you have the code: https://github.com/miguelgfierro/sciblog

hoaphumanoidon A Gentle Introduction to the Basics of Machine Learning

I believe that the best way to learn ML is by first learning to program the algorithms and then learning the math. This is the opposite to what people is used to do, but I think it's better. The reason is because programming ML is easy, but the math behind it is very complex. I would suggest to start with scikit tutorial http://scikit-learn.org/stable/tutorial/ and later with Ng course https://www.coursera.org/learn/machine-learning. Then a good book is Pattern Recognition and Machine Learning, from Bishop.

hoaphumanoidon Lessons learned about marketing while building a startup

Hehehe yes I'm a little geek ;-) the code is on github if you want it

hoaphumanoidon About “What is happening with this world?”

Too much TV

hoaphumanoidon Geoffrey Hinton: Introduction to Deep Learning, Deep Belief Nets (2012) [video]

His coursera lectures are awesome

hoaphumanoidon What is scrum and how to apply it to a startup

Could you try to act as an unofficial product owner? Like trying to do everything right but without explicitly saying it

hoaphumanoidon What is scrum and how to apply it to a startup

Totally agree

hoaphumanoidon A blog with the appearance of a scientific paper

The idea is to do the same design as in a scientific paper. As a framework I use django and python. The font is the default font of Latex, which is the framework that is used in many sciences to write a paper.

I will explain how the blog is done in a future post. It's not focused yet. Thanks

hoaphumanoidon A blog with the appearance of a scientific paper

Hi I'm starting a blog related to startups, science, robotics and AI. Its design is like a scientific paper. Any advice is welcomed