Stanford - The Natural Language Processing Course


Long time ago, when the first courses about natural language procession and machine learning had released, I was planning to get them. I announced around and let people know what they could have, what they couldn’t. In short, I was excited. But years were passing and I couldn’t have attend because of short of time and being very busy.

A few weeks ago I was contemplating about tf-idf. I looked for it and read some pages and continued to search, eventually run across the nlp course. I watched the related videos, since then I’ve been continuing.

Learning something for need is much better than learning to fill spare time.

Comments

Post a Comment

Popular posts from this blog

(DRAFT) Scaling a django project using celery and elasticsearch

Scalability has undoubtedly become an important asset not only for large software projects but also mid-level ones now. Indeed, when you have a look at developer job posts, you can see easily that the need to build scalable software is one of the top desired skills. Making a software scalable requires mostly more than one methodology and different technology stacks. At first, it may look difficult and require deep experience with those methods and stacks. And yes, scalability is a serious topic. Although it is, in this post, I will show how to make a Django application scalable. In the end, you will learn fundamental concepts and approaches. PLAN create a django project which is a little product management system. make adding product asynchronous instead of synchronous sync elasticsearch with the primary database ( SQLite ) use elasticsearch for autocomplete and real-time analysis 1. Product management app with Django Since I assume you are familiar with Python an...
Read more

Euclidean Distance (similarity)

Bir kümedeki elementlerin benzerliğini ölçen, benzerlik puanı üreten avantajı ve dezavantajı duruma göre değişen algoritmalar bulunmaktadır. Collaborative Intelligence kitabında Euclidean Distance hesaplaması ile film eleştirmenleri arasındaki benzerlik hesaplanmıştır. Senaryoda, kişiler çeşitli filmlere puan vermişlerdir ve bu puanlar üzerinden bir kişinin diğer insanlarla arasındaki benzerlik hesaplanmıştır.Birkaç ekleme dışında kodların tamamını kitaptaki gibi aktarıyorum. from math import sqrt def sim_euclidan_distance(prefs, person1, person2): si={} for item in prefs[person1]: if item in prefs[person2]: si[item]=1 if len(si)==0: return 0 sum_of_squares=sum([ pow( prefs[person1][item]-prefs[person2][item], 2) for item in prefs[person1] if item in prefs[person2] ]) return 1/(1+sqrt(sum_of_squares)) critics={ 'Mustafa': { "The Matrix": 5, "The Godfather": 5, "Se7en": 3, "Babel": 2, "Troy": 4, ...
Read more