Monthly Archives: January 2015

My recent work in Recommendation System

Need time to write up.
http://docs.prediction.io/community/showcase/

Description:

Yelp is an online urban guide that helps people find recommended destinations based on the informed opinions and reviews of a community.

Goal: the high level goal of this project is to apply existing built-in PredictionIO engines to a new domain and new dataset.

For this project you will build a restaurant recommendation engine (see Yelp) using built-in Item Recommendation engine and the Yelp dataset.

Dataset:

Yelp dataset via Kaggle – https://www.kaggle.com/c/yelp-recsys-2013/data

Demo link:

http://yelpio.hongo.wide.ad.jp/

http://zorovn.hongo.wide.ad.jp/

Link

i\hbar\frac{\partial}{\partial t}\left|\Psi(t)\right>=H\left|\Psi(t)\right>

Deep Learning + NLP (PFIの勉強会)

  1. Deep Learning とは?
    • Neural Network (input, hidden, output) の拡張: hidden layers >= 2(階層を増やす)
    • Hidden layers:
      • Deep Brief Network
      • Convolutional Neural Network (image recognition)
      • Stacked Auto Encoder
      • Recursive NN
      • Recurrence NN
    • 画像認識精度アップ、音声認識、薬物の活性の推測
      Continue reading