data science · machine learning

Deep Learning – NLP Home Word2Vec: CBOW, skip-grams | Glove (cannot solve the problem of synonyms) ELMo (Embedding from Language Models): Deep contextualized word representation Instead of using a fixed embedding for each word, ELMo looks at the entire sentence before assigning each word in it an embedding. It uses a bi-directional LSTM trained on a specific… Continue reading Deep Learning – NLP

data science · machine learning

Interpretability of ML Global Interpretability Partial Dependence and Partial Dependence Plot (PDP) Individual Conditional Expectation (ICE) Total and two-way H Statistics Global Feature importance using permutation Global surrogate model Local Interpretability Local Interpretable Model-agnostic Explanations (LIME) Shapley additive explanation An intuitive way to understand the Shapley value is the following illustration: The feature values enter a… Continue reading Interpretability of ML

Big Data · Data Engineering · industry

Data in Real Scenarios

Log Management: logs are events with timestamps. Multi-cloud for regulatory reasons, and can handle the fail over of a single cloud. Elastic Search: full text searching, distributed? implicit index URBN: fashion product attribution. planning & forecasting; search correlation (Fashion MNIST data set) Linkedin: scaled of machine learning using graph database (neo4j), second degree. predicting future… Continue reading Data in Real Scenarios