Machine Learning Resources

Courses

• Machine Learning Specialization. Coursera: Stanford University and DeepLearning.AI
• Deep Learning Specialization. Coursera: DeepLearning.AI

Newsletters

• The Batch: DeepLearning.AI.
• OpenAI Dev Digest.

Books

• Aurélien Geron. Hands-On Machine Learning with Scikit-Learn & TensorFlow
• Noah Gift, Alfredo Deza. Practical MLOps: Operationalizing Machine Learning Models
• Chip Huyen. AI Engineering: Building Applications with Foundational Models

Math, Statistics

• Peter Bruce, Andrew Bruce, Peter Gedeck. Practical Statistics for Data Scientists: 50+ Essential Concepts using R and Python
• Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong. Mathematics for Machine Learning
• Andriy Burkov. The Hundred-Page Machine Learning Book
• Trevor Hastie, Robert Tibshirani, Jerome Friedman. The Elements of Statistical Learning

Time Series

• Rob J Hyndman & George Athanasopoulos. Forecasting: Principles and Practice
• James D. Hamilton. Time Series Analysis

Causal Inference

• Matheus Facure Alves. Causal Inference for the Brave and True
• Scott Cunningham. Causal Inference: The Mixtape

Finance

• Hilpisch, Yves. Python for Finance: Mastering Data-Driven Finance

LLMs

• Jay Alammar, Maarten Grootendorst. Hands-On Large Language Models
• Daniel Jurafsky & James H. Martin. Speech and Language Processing

Advanced Python

• Luciano Ramalho. Fluent Python: Clear, Concise, and Effective Programming
• Leonardo Giordani. Clean Architectures in Python
• Bob Gregory & Harry Percival. Architecture Patterns with Python: Enabling Test-Driven Development, Domain-Driven Design, and Event-Driven Microservices
• Micha Gorelick & Ian Ozsvald. High Performance Python: Practical Performant Programming for Humans
• David M. Beazley. Python Distilled

Econometrics

• Joshua Angrist. Mostly Harmless Econometrics
• William H. Greene. Econometric Analysis
• Jeffrey Wooldridge. “Analysis of Cross Section and Panel Data”

Others

• Pedro Domingos. The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World
• Valliappa Lakshmanan, Sara Robinson & Michael Munn. Machine Learning Design Patterns: Solutions to Common Challenges in Data Preparation, Model Bulding, and MLOps
• Robert C. Martin. Clean Code: A Handbook of Agile Software Craftsmanship
• David Spiegelhalter. The Art of Statistics: Learning from Data
• Brent Dykes. Effective Data Storytelling: How to Drive Change with Data, Narrative and Visuals
• Mastering Metrics

Glossary

• AD Autodiff (automatic differentiation)
• ML Machine Learning
• DL Deep learning
• BERT Bidirectional Encoder Representations from Transformers
• NLP Natural Language Processing
• NER Named Entity Recognition
• QA Question Answerings
• GPT Generative Pre-trained Transformer
• GBDT Gradient-boosted decision trees
• XGBoost eXtreme Gradient Boosting
• SVM Support Vector Machine
• GRU Gated Recurrent Unit
• LSTM Long Short-Term Memory
• MFCC Mel Frequency Cepstral Coefficients
• LRN Local Response Normalization
• RBM Restricted Boltzmann machine
• EDA Exploratory Data Analysis
• ETL Extract, Transform, Load
• MARS Multivariate Adaptive Regression Splines
• GAN Generative Adversarial Networks
• LGBM Light gradient-boosting machine
• RF Random Forest
• KDE Kernel Density Estimate
• DBSCAN Density-based spatial clustering of applications with noise
• BIRCH Balance Iterative Reducing and Clustering using Hierarchies
• OPTICS Ordering Points to Identify the Clustering Structure
• RFM Recency, Frequency, Monetary model
• NPS Net Promoter Score
• LoRA Low-Rank-Adaption of Large Language Model
• LLM Large Language Model
• PEFT Parameter-efficient fine-tuning
• ARL Association Rule Learning
• GLM Generalized Linear Model

Visualization

• PCA Principal Component Analysis
• t-SNE T-Distributed stochastic neighbor embedding (also TSNE)
• LDA Linear Discriminant Analysis
• UMAP Uniform Manifold Approximation and Projection

Neural Networks

• BRNN Bidirectional Recurrent Neural Network
• RNN Recurrent Neural Network
• CNN Convolutional Neural Network
• DNN Deep Neural Network
• R-CNN Region Based Convolutional Neural Network

Metrics

• ROC (ROC curve) Receiver Operating Characteristic curve. Plots sensitivity vs. 1-specificity (TPR vs. FPR)
• AUC Area under the ROC curve. Source: Google Course.
• TPR True Positive Rate $\text{TPR}=\frac{tp}{tp+fn}$ (Recall, sensitivity)
• FPR False Positive Rate $\text{FPR}=\frac{fp}{fp+tn}=1-\text{TNR}$ (fall-out)
• TNR True Negative Rate: specificity

Time Series

• STL Seasonal and Trend decomposition using Loess
• ARIMA Autoregressive integrated moving average
• SVD Singular Value Decomposition
• UCM Unobserved Components Model