nlp-love/ml-nlp

★ 17,665Jupyter NotebookAudience · dataComplexity · 2/5Setup · easy

Mindmap

mindmap
  root((repo))
    What it does
      Interview prep
      ML and NLP study
    Machine Learning
      Decision trees
      Gradient boosting
      SVM and clustering
    Deep Learning
      CNN RNN LSTM
      Transformers
      Reinforcement learning
    NLP
      Word embeddings
      BERT and XLNet
      seq2seq attention

mindmap root((repo)) What it does Interview prep ML and NLP study Machine Learning Decision trees Gradient boosting SVM and clustering Deep Learning CNN RNN LSTM Transformers Reinforcement learning NLP Word embeddings BERT and XLNet seq2seq attention

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Review machine learning interview topics like decision trees, XGBoost, and SVMs with theory and working code side by side.

USE CASE 2

Study NLP concepts including word embeddings, attention mechanisms, and transformers to prepare for an algorithm engineer interview.

USE CASE 3

Work through deep learning topics like CNNs, RNNs, and LSTMs systematically using the numbered curriculum.

Tech stack

PythonJupyter Notebook

Getting it running

Difficulty · easy Time to first run · 5min

In plain English

ML-NLP is a study-and-revision collection aimed at people preparing for machine-learning, deep-learning, and natural-language-processing job interviews, particularly in China. The author treats it as foundational theory an algorithm engineer is expected to know, arranged in numbered modules so a reader can dip in for review or work through as a curriculum. Each chapter focuses on a topic interviews tend to probe, and most chapters end with hands-on code that connects the math to a working implementation. The machine-learning module covers classic supervised methods: linear regression, logistic regression, decision trees, random forests, gradient-boosted trees, XGBoost, LightGBM, and support vector machines, followed by probabilistic graphical models (Bayesian networks, Markov, topic models), expectation-maximization, clustering, feature engineering, and k-nearest neighbours. The deep-learning module walks through neural networks, convolutional networks, recurrent networks, GRUs, LSTMs, transfer learning, reinforcement learning, and optimization. The NLP module covers word embeddings (Word2Vec, fastText, GloVe), text-classification models like textRNN and textCNN, seq2seq, attention, and the Transformer family including BERT and XLNet. A projects section sketches applied examples: recommendation, intelligent customer service, knowledge graphs, and sentiment analysis. Someone would use this repository to refresh interview topics quickly, build a personal knowledge map, or fill gaps before tackling a specific algorithm. The materials are Markdown explanations alongside Jupyter Notebooks for code, and the project is updated continuously and welcomes contributions.

Copy-paste prompts

Prompt 1

I have an ML interview next week and need to review gradient-boosted trees quickly. Walk me through the XGBoost content from ml-nlp and quiz me on the key concepts.

Prompt 2

Help me understand the Transformer architecture using the ml-nlp study materials. Explain attention mechanisms in plain English and show me the key equations.

Prompt 3

I am weak on probabilistic graphical models for a data science interview. Using ml-nlp as a reference, explain Bayesian networks and Markov models with simple examples.

Prompt 4

How does ml-nlp cover BERT and XLNet? Summarize the key differences between the two and what interview questions each model tends to generate.

Open on GitHub → Explain another repo

← nlp-love on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.