Learning

This repo is based on the amazing repo from amitness, go check!

Quick Access:

• Learning Philosophy
• Be able to perform A/B testing
• Be able to use experiment management tool
• Be familiar with Recommendation Systems
• Be able to model problems mathematically
• Be familiar with ML System/MLOps
• Be able to implement computer vision models

Learning Philosophy:

• Data Scientists Should Be More End-to-End
• Just in Time Learning
• Master Adjacent Disciplines
• T-shaped skills
• The Power of Tiny Gains

Be able to frame an ML problem

• Coursera: Structuring Machine Learning Projects

Be able to perform A/B testing

• Article: Multi-Armed Bandit (MAB) – A/B Testing Sans Regret
• Article: When to Run Bandit Tests Instead of A/B/n Tests
• Article: A/B Testing Machine Learning Models (Deployment Series: Guide 08)
• Datacamp: Customer Analytics & A/B Testing in Python
• Udacity: A/B Testing
• Udacity: A/B Testing for Business Analysts
• Youtube: Hypothesis testing with Applications in Data Science 0:10:33
• Article: How Netflix uses A/B tests to make decisions Netflix
  • Decision Making at Netflix (Part 1)
  • What is an A/B Test? (Part 2)
  • Interpreting A/B test results: false positives and statistical significance (Part 3)
  • Interpreting A/B test results: false negatives and power (Part 4)
• A/B Testing and Beyond: Improving the Netflix Streaming Experience with Experimentation and Data Science Netflix
• Quasi Experimentation at Netflix Netflix
• Universal Holdout Groups at Disney Streaming Disney

Be able to use experiment management tool

• Building an Intelligent Experimentation Platform with Uber Engineering Uber
• Under the Hood of Uber’s Experimentation Platform
• DARWIN: Data Science and Artificial Intelligence Workbench at LinkedIn LinkedIn

Be familiar with Recommendation Systems

• My RecSys studies can be found on this repo

Be able to model problems mathematically

• 3Blue1Brown: Essence of Calculus
  • The Essence of Calculus, Chapter 1 0:17:04
  • The paradox of the derivative | Essence of calculus, chapter 2 0:17:57
  • Derivative formulas through geometry | Essence of calculus, chapter 3 0:18:43
  • Visualizing the chain rule and product rule | Essence of calculus, chapter 4 0:16:52
  • What's so special about Euler's number e? | Essence of calculus, chapter 5 0:13:50
  • Implicit differentiation, what's going on here? | Essence of calculus, chapter 6 0:15:33
  • Limits, L'Hôpital's rule, and epsilon delta definitions | Essence of calculus, chapter 7 0:18:26
  • Integration and the fundamental theorem of calculus | Essence of calculus, chapter 8 0:20:46
  • What does area have to do with slope? | Essence of calculus, chapter 9 0:12:39
  • Higher order derivatives | Essence of calculus, chapter 10 0:05:38
  • Taylor series | Essence of calculus, chapter 11 0:22:19
  • What they won't teach you in calculus 0:16:22
• 3Blue1Brown: Essence of linear algebra
  • Vectors, what even are they? | Essence of linear algebra, chapter 1 0:09:52
  • Linear combinations, span, and basis vectors | Essence of linear algebra, chapter 2 0:09:59
  • Linear transformations and matrices | Essence of linear algebra, chapter 3 0:10:58
  • Matrix multiplication as composition | Essence of linear algebra, chapter 4 0:10:03
  • Three-dimensional linear transformations | Essence of linear algebra, chapter 5 0:04:46
  • The determinant | Essence of linear algebra, chapter 6 0:10:03
  • Inverse matrices, column space and null space | Essence of linear algebra, chapter 7 0:12:08
  • Nonsquare matrices as transformations between dimensions | Essence of linear algebra, chapter 8 0:04:27
  • Dot products and duality | Essence of linear algebra, chapter 9 0:14:11
  • Cross products | Essence of linear algebra, Chapter 10 0:08:53
  • Cross products in the light of linear transformations | Essence of linear algebra chapter 11 0:13:10
  • Cramer's rule, explained geometrically | Essence of linear algebra, chapter 12 0:12:12
  • Change of basis | Essence of linear algebra, chapter 13 0:12:50
  • Eigenvectors and eigenvalues | Essence of linear algebra, chapter 14 0:17:15
  • Abstract vector spaces | Essence of linear algebra, chapter 15 0:16:46
• 3Blue1Brown: Neural networks
  • But what is a Neural Network? | Deep learning, chapter 1 0:19:13
  • Gradient descent, how neural networks learn | Deep learning, chapter 2 0:21:01
  • What is backpropagation really doing? | Deep learning, chapter 3 0:13:54
  • Backpropagation calculus | Deep learning, chapter 4 0:10:17
• Article: A Visual Tour of Backpropagation
• Article: Entropy, Cross Entropy, and KL Divergence
• Article: Interview Guide to Probability Distributions
• Article: Introduction to Linear Algebra for Applied Machine Learning with Python
• Article: Entropy of a probability distribution — in layman’s terms
• Article: KL Divergence — in layman’s terms
• Article: Probability Distributions
• Article: Relearning Matrices as Linear Functions
• Article: You Could Have Come Up With Eigenvectors - Here's How
• Article: PageRank - How Eigenvectors Power the Algorithm Behind Google Search
• Article: Interactive Visualization of Why Eigenvectors Matter
• Article: Cross-Entropy and KL Divergence
• Article: Why Randomness Is Information?
• Article: Basic Probability Theory
• Article: Math You Need to Succeed In ML Interviews
• Book: Basics of Linear Algebra for Machine Learning
• Datacamp: Introduction to Statistics in Python
• Datacamp: Foundations of Probability in Python
• Datacamp: Statistical Thinking in Python (Part 1)
• Datacamp: Statistical Thinking in Python (Part 2)
• Datacamp: Statistical Simulation in Python
• edX: Essential Statistics for Data Analysis using Excel
• Computational Linear Algebra for Coders
• Khan Academy:
  • Khan Academy: Precalculus
  • Khan Academy: Probability
  • Khan Academy: Differential Calculus
  • Khan Academy: Multivariable Calculus
  • Khan Academy: Linear Algebra
• MIT: 18.06 Linear Algebra (Professor Strang)
  • 1. The Geometry of Linear Equations 0:39:49
  • 2. Elimination with Matrices. 0:47:41
  • 3. Multiplication and Inverse Matrices 0:46:48
  • 4. Factorization into A = LU 0:48:05
  • 5. Transposes, Permutations, Spaces R^n 0:47:41
  • 6. Column Space and Nullspace 0:46:01
  • 9. Independence, Basis, and Dimension 0:50:14
  • 10. The Four Fundamental Subspaces 0:49:20
  • 11. Matrix Spaces; Rank 1; Small World Graphs 0:45:55
  • 14. Orthogonal Vectors and Subspaces 0:49:47
  • 15. Projections onto Subspaces 0:48:51
  • 16. Projection Matrices and Least Squares 0:48:05
  • 17. Orthogonal Matrices and Gram-Schmidt 0:49:09
  • 21. Eigenvalues and Eigenvectors 0:51:22
  • 22. Diagonalization and Powers of A 0:51:50
  • 24. Markov Matrices; Fourier Series 0:51:11
  • 25. Symmetric Matrices and Positive Definiteness 0:43:52
  • 27. Positive Definite Matrices and Minima 0:50:40
  • 29. Singular Value Decomposition 0:40:28
  • 30. Linear Transformations and Their Matrices 0:49:27
  • 31. Change of Basis; Image Compression 0:50:13
  • 33. Left and Right Inverses; Pseudoinverse 0:41:52
• StatQuest: Statistics Fundamentals
  • StatQuest: Histograms, Clearly Explained 0:03:42
  • StatQuest: What is a statistical distribution? 0:05:14
  • StatQuest: The Normal Distribution, Clearly Explained!!! 0:05:12
  • Statistics Fundamentals: Population Parameters 0:14:31
  • Statistics Fundamentals: The Mean, Variance and Standard Deviation 0:14:22
  • StatQuest: What is a statistical model? 0:03:45
  • StatQuest: Sampling A Distribution 0:03:48
  • Hypothesis Testing and The Null Hypothesis 0:14:40
  • Alternative Hypotheses: Main Ideas!!! 0:09:49
  • p-values: What they are and how to interpret them 0:11:22
  • How to calculate p-values 0:25:15
  • p-hacking: What it is and how to avoid it! 0:13:44
  • Statistical Power, Clearly Explained!!! 0:08:19
  • Power Analysis, Clearly Explained!!! 0:16:44
  • Covariance and Correlation Part 1: Covariance 0:22:23
  • Covariance and Correlation Part 2: Pearson's Correlation 0:19:13
  • StatQuest: R-squared explained 0:11:01
  • The Central Limit Theorem 0:07:35
  • StatQuickie: Standard Deviation vs Standard Error 0:02:52
  • StatQuest: The standard error 0:11:43
  • StatQuest: Technical and Biological Replicates 0:05:27
  • StatQuest - Sample Size and Effective Sample Size, Clearly Explained 0:06:32
  • Bar Charts Are Better than Pie Charts 0:01:45
  • StatQuest: Boxplots, Clearly Explained 0:02:33
  • StatQuest: Logs (logarithms), clearly explained 0:15:37
  • StatQuest: Confidence Intervals 0:06:41
  • StatQuickie: Thresholds for Significance 0:06:40
  • StatQuickie: Which t test to use 0:05:10
  • StatQuest: One or Two Tailed P-Values 0:07:05
  • The Binomial Distribution and Test, Clearly Explained!!! 0:15:46
  • StatQuest: Quantiles and Percentiles, Clearly Explained!!! 0:06:30
  • StatQuest: Quantile-Quantile Plots (QQ plots), Clearly Explained 0:06:55
  • StatQuest: Quantile Normalization 0:04:51
  • StatQuest: Probability vs Likelihood 0:05:01
  • StatQuest: Maximum Likelihood, clearly explained!!! 0:06:12
  • Maximum Likelihood for the Exponential Distribution, Clearly Explained! V2.0 0:09:39
  • Why Dividing By N Underestimates the Variance 0:17:14
  • Maximum Likelihood for the Binomial Distribution, Clearly Explained!!! 0:11:24
  • Maximum Likelihood For the Normal Distribution, step-by-step! 0:19:50
  • StatQuest: Odds and Log(Odds), Clearly Explained!!! 0:11:30
  • StatQuest: Odds Ratios and Log(Odds Ratios), Clearly Explained!!! 0:16:20
  • Live 2020-04-20!!! Expected Values 0:33:00
• Udacity: Eigenvectors and Eigenvalues
• Udacity: Linear Algebra Refresher
• Udacity: Statistics
• Udacity: Intro to Descriptive Statistics
• Udacity: Intro to Inferential Statistics
• StatsCast: What is a t-test? 0:09:56
• Coursera: Linear Algebra for Machine Learning and Data Science

Be familiar with ML System/MLOps

• The Magic of Merlin: Shopify's New Machine Learning Platform Shopify 2022
• Coursera: Introduction to Machine Learning in Production

Computer Vision

• Youtube: Deep Learning for Video Summarization 0:47:40

  IQA

  • Paper: Browsing and Sorting Digital Pictures Using Automatic Image Classification and Quality Analysis
  • Paper: Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study
  • Article: Image Quality Assessment : BRISQUE
  • Paper: Multimedia Features for Click Prediction of New Ads in Display Advertising