No, they are not. But they have a number of similarities that might be unexpected when you first learn a certain algorithm, such as Word2Vec or GloVe. This post is a summary of a series of papers that I found in the latest years, which show aspects common to word embedding methods that have been … Continue reading Are All Word Embeddings the Same?
Explainable Machine Learning with Lasso Logistic Regression
Explainable Artificial Intelligence (now fancily abbreviated as XAI) is a growing trend in the latest years. It is a logical consequence of the development of predictive algorithms of evergrowing complexity, namely deep learning systems such as CNNs. Such systems are undoubtedly qualified as black-boxes, because they don't provide a straightforward interpretation of their decisions. You … Continue reading Explainable Machine Learning with Lasso Logistic Regression
Book advice: The Book of Why
"If causation is not correlation, what is it?" How many times have you repeated the mantra "correlation does not mean causation"? I did, plenty of times, and for good reason. Any attempt to interpret or explain a machine learning model should keep in mind that two variables happening together does not mean that one causes … Continue reading Book advice: The Book of Why
My History: an Information Guy
I'm part of the Millennial generation. I was born when a Game Boy was a kid's most valuable treasure; when there was no video-on-demand platforms, so TV audiences were dramatically higher than nowadays, and you spent the next day commenting on how good the show was. Mobile phones were heavy bricks and Snake was our … Continue reading My History: an Information Guy