Advanced Data Science

A 6-part series of hands-on Jupyter notebooks covering advanced data science topics. The sequel to Foundations of Data Science.

Notebooks

#	Notebook	Topics
0	Table of Contents	Series overview, learning path, prerequisites
1	Unsupervised Learning	K-means, hierarchical clustering, DBSCAN, PCA
2	Probabilistic Modeling	Bayesian inference, PyMC, MCMC, hierarchical models
3	Neural Networks	Backpropagation from scratch, Keras, regularization
4	Convolutional Neural Networks	Convolution, Fashion-MNIST, data augmentation, transfer learning
5	Sequence Models and NLP	RNN, LSTM, GRU, bidirectional models, text generation
6	Attention and Transformers	Multi-head attention, positional encoding, Vision Transformer

Completion of Foundations of Data Science or equivalent knowledge of Python, statistics, and supervised learning
Python 3.9+

pip install -r requirements.txt

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
.gitignore		.gitignore
00_table_of_contents.ipynb		00_table_of_contents.ipynb
01_unsupervised_learning.ipynb		01_unsupervised_learning.ipynb
02_probabilistic_modeling.ipynb		02_probabilistic_modeling.ipynb
03_neural_networks.ipynb		03_neural_networks.ipynb
04_convolutional_neural_networks.ipynb		04_convolutional_neural_networks.ipynb
05_sequence_models_and_nlp.ipynb		05_sequence_models_and_nlp.ipynb
06_attention_and_transformers.ipynb		06_attention_and_transformers.ipynb
README.md		README.md
requirements.txt		requirements.txt