The First Cry of Atom

How can we estimate the loss of a machine learning model based on its complexity? We know that complex model can explain various kinds of data set space but it can overfit to the sample space. We want to optimize the loss in whole data space instead of sample space.... [Read More]

Now database migration should be managed under version control system. Every database schema can be changed through time. If we don’t track this, it must be difficult to rollback or test. We often use ActiveRecord as migration script because it is database agnostic and easy to write. [Read More]

As you know, Java 8 provides lambda expression and stream API. forEach is one of the them. [Read More]

Neural Networkにおいて最適化の中心を担うのはBackpropagation(誤差逆伝播法)ですが、Recurrent Neural Networkではどのように計算されるのかよくわからなかったので、まとめてみました。 [Read More]

When I wrote a test for Finagle, I found it didn’t work as expected. Scalatest didn’t check assertion properly asynchronously like Future. [Read More]