Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
User-based Filtering (Memory-based Filtering)
Item-based Filtering (Content-based Filtering)
Non-negative Matrix Factorization
Neural Matrix Factorization
Variational Autoencoder
Hybrid
New methods like VAE, AE, or Deep Collaborative outperform classical methods like NMF on …
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
GELU is the best activation function currently (at least in NLP).
,
where \(\Phi(x)\) is the cumulative distribution function of the standard normal distribution.
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
http://nlp.seas.harvard.edu/2018/04/03/attention.html
https://blog.floydhub.com/the-transformer-in-pytorch/
http://jalammar.github.io/illustrated-transformer/
https://towardsdatascience.com/transformers-141e32e69591
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
https://en.wikipedia.org/wiki/Feature_scaling
https://www.jeremyjordan.me/batch-normalization/
How to use Data Scaling Improve Deep Learning Model Stability and Performance
https://medium.com/@urvashilluniya/why-data-normalization-is-necessary-for-machine-learning-models-681b65a05029
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
http://www.wildml.com/2016/01/attention-and-memory-in-deep-learning-and-nlp/
https://medium.com/@joealato/attention-in-nlp-734c6fa9d983
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
https://code.google.com/archive/p/word2vec/
Google Word2Vec claims that hierarchical softmax is better for infrequent words while negative sampling is better for frequent words …