Movie Recommendation
This is the final project of NTDS course. Our team uses date sets from kaggle. As we first wrote our own project for recommendation engine, this project seems a little bit simple.
Chinese GIRL from Chengdu
Love coding (a little bit)
Interest in Machine Learning, Deep Learning and Food
Projects are always courses' projects at EPFL. SAD ðŸ˜. I am trying to enhance my experience!
This is the final project of NTDS course. Our team uses date sets from kaggle. As we first wrote our own project for recommendation engine, this project seems a little bit simple.
This is the final project of Lab of Data science course. We used the data published by the Open Data Platform Swiss Public Transport (https://opentransportdata.swiss). This project is not only plan a journey like google maps but also need to consider the probabilities of failure when journey containing transmits.
I planned to write some blogs on paper reading, unix, shell and something I should remember and know.
Pre-processing raw text data is basic and essential step for NLP tasks. Classic word representation cannot handle unseen word or rare word well. Character embeddings is one of the solution to overcome out-of-vocabulary (OOV). However, it may too fine-grained any missing some important information. Subword is in between word and character. It is not too fine-grained while able to handle unseen word and rare word.
Basic usage of tensorflow.
If you would like to discuss questions on what I have post, please do not hesitate to contact me.