It’s been a while since I blogged about neural networks and how to use them to rank a set of items based on the users’ preferences. The blog was in 2015 and a lot has happened since then. I think it might be a good time to recap some of the resources that I stumbled upon over this period.
Hope you enjoy this random selection of links!
A random article or paper
When I started looking at pairwise ranking in this article a few years ago the community was quite young. I was very pleased to see that in 2018 Airbnb published this article presenting their results using a real production dataset. The article does not only show the end result but also walks you through some of the failures they had along the journey. Inspirational!
A random video or podcast
A random book
A random tool
A random line of code
train = RubyFann::TrainData.new(:inputs=>[[0.3, 0.4, 0.5], [0.1, 0.2, 0.3]], :desired_outputs=>[[0.7], [0.8]])
fann = RubyFann::Standard.new(:num_inputs=>3, :hidden_neurons=>[2, 8, 4, 3, 4], :num_outputs=>1)
fann.train_on_data(train, 1000, 10, 0.1) # 1000 max_epochs, 10 errors between reports and 0.1 desired MSE (mean-squared-error)
outputs = fann.run([0.3, 0.2, 0.4])
A random quote
If you can’t explain it to a six year old, you don’t understand it yourself.Albert Einstein