Born, Life, and the Hereafter. A life journal.
When we discuss prediction models, prediction errors can be decomposed into two main subcomponents we care about: error due to “bias” and error due to “variance”. There is a tradeoff between a model’s ability to minimize bias and variance. Understanding these two types of error can help us diagnose model results and avoid the mistake of over- or under-fitting.
http://scott.fortmann-roe.com/docs/BiasVariance.html
[contentblock id=1 img=adsense.png]
Full repost dari Status Updatenya bang Darwis Tere Liye sebagai note untuk diri sendiri.
—
*Hakikat belajar
Orang dewasa, saat ditanya, kenapa kita belajar menulis? Kalau jawabannya: agar bisa menerbitkan buku. Maka itu benar2 membelokkan tujuan mulia dari menulis. Saat ditanya, kenapa kita belajar memasak? Kalau jawabannya: agar bisa jadi master cheft, punya restoran mahal, maka itu juga benar2 membelokkan tujuan mulia dari memasak. Orang dewasa, saat ditanya, kenapa sekolah tinggi2? Kalau jawabannya: agar bisa kaya raya, berkuasa, maka itu benar2 membelokkan tujuan mulia dari mencari ilmu.
If you don’t give up, you can not fail
Sebenarnya, rahasia dari menguasai keahlian apapun bukan terletak pada motivasi, karena motivasi hanya kunci pembuka awalnya saja, tapi ibu dari segala keahlian adalah pengulangan (repetisi) dan ayahnya adalah latihan (practice). Bila seseorang banyak melatih dan mengulang, terpaksa ataupun sukarela, dia pasti akan menguasai keahlian tertentu. Inilah namanya pembentukan kebiasaan (habits)
Ust. Felix Siauw
Sumber: http://felixsiauw.com/home/menguasai-keahlian-dengan-pembiasaan-habits/
Simple but rough implementation of EM-algorithm for unsupervised learning in case of fitting a mixture of 3 multivariate Gaussian to the Fisher Iris data set as well as fitting the means and covariance matrices. Continue reading “Python: Unsupervised Learning using EM-Algorithm Implementation”
[contentblock id=1 img=adsense.png]
Simple, quick and dirty implementation about k-nearest neighbours (KNN) algorithm for classification (k nearest neighbours classifier) in Python 2.75 with NumPy and SciPy help. You may want to read about the KNN on Wiki. Anyway, here is the code. You may also observe the dataset first to help you understand the code. Continue reading “Python: Simple K Nearest Neighbours Classifier”
This link details how to implement the MVC design pattern for games and its implementation in Python.
Mercurial is a modern, open source, distributed version control system, and a compelling upgrade from older systems like Subversion. In this user-friendly, six-part tutorial, Joel Spolsky teaches you the key concepts. Also, Fog Creek offers free monthly webinars that go over the basics of Mercurial.
To start this quick review about Scala as Java.Next, let us see an interesting perceptive observation from Martin Fowler about Java and its legacy as follows.
“The legacy of Java will be the platform, not the language”
This statement is interested since more than 200 languages run on Java Virtual Machine (JVM) nowadays [1]. This condition emerges since Oracle hosted the annual JVM Language Summit in 2008, which has given implementers of alternative languages on the JVM an opportunity to collaborate openly with Java platform engineers. For example, let us consider Clojure, Groovy, Scala, and the new one, Kotlin. Each language brings interesting new capabilities beyond of Java language itself. In general, two initial significant advantages that these languages tend to provide are reducing the amount of verbosity in code. Hence it allows us to focus on the essence of problem solving. The second advantage is enabling some degree of functional programming styles [2]. This short review will be limited to Scala as an alternative programming language of Java.
As introduced in their official website [3], Scala is an elegant and concise programming language that integrates both functional and object-oriented paradigms smoothly. This enabling programmers to be more productive while retaining full interoperability with Java and taking advantage of modern multicore hardware. It is statically typed and well found with an expressive type system, which supports: generic classes, variance annotations, upper and lower type bounds, inner classes and abstract types as object members, compound types, explicitly typed self references, views, and polymorphic methods.
Continue reading “From Java to Java.Next – Quick Review of Scala”