https://github.com/amitness/learning
Becoming 1% better at data science everyday
learning 
Learning Philosophy:
Develop a business acumen
Be able to frame a ML problem
Understand data ethics better
Be able to annotate data efficiently
Be able to manipulate data with Numpy
Be able to manipulate data with Pandas
Be able to manipulate data in spreadsheets
Be able to manipulate data in databases
Be able to use the command line
Be able to import data from multiple sources
Be able to perform feature engineering
Be able to experiment in notebook
Be able to visualize data
Be able to to read research papers
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
- Article: A Visual Tour of Backpropagation
- 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
- Book: Basics of Linear Algebra for Machine Learning
- 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: Precalculus
- Khan Academy: Probability
- Khan Academy: Differential Calculus
- Khan Academy: Multivariable Calculus
- Khan Academy: Linear Algebra
- MIT: 18.06 Linear Algebra (Professor Strang)
- 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
- Bam!!! Clearly Explained!!!
0:02:49
- 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: Algebra Review
- Udacity: Differential Equations in Action
- Udacity: Eigenvectors and Eigenvalues
- Udacity: Linear Algebra Refresher
- Udacity: Statistics
- Udacity: Intro to Descriptive Statistics
- Udacity: Intro to Inferential Statistics
- Youtube: Principal Component Analysis (PCA) - THE MATH YOU SHOULD KNOW!
0:10:06
- Youtube: Support Vector Machines - THE MATH YOU SHOULD KNOW
0:11:21
- Youtube: The Kernel Trick - THE MATH YOU SHOULD KNOW!
0:07:29
- Youtube: Logistic Regression - THE MATH YOU SHOULD KNOW!
0:09:14
- Youtube: But what is a Neural Network? - THE MATH YOU SHOULD KNOW!
0:19:07
Be able to structure machine learning projects
Be able to utilize version control
Be familiar with a breadth of models and algorithms
- Article: Label Smoothing Explained using Microsoft Excel
- Article: Naive Bayes classification
- Article: Linear regression
- Article: Polynomial regression
- Article: Logistic regression
- Article: Decision trees
- Article: K-nearest neighbors
- Article: Support Vector Machines
- Article: Random forests
- Article: Boosted trees
- Article: Neural networks: activation functions
- Article: Neural networks: training with backpropagation
- Article: Gradient descent
- Article: Setting the learning rate of your neural network
- Article: Deep neural networks: preventing overfitting
- Article: Normalizing your data (specifically, input and batch normalization)
- Article: Batch Normalization
- Article: Baidu Deep Voice explained: Part 1 — the Inference Pipeline
- Article: Baidu Deep Voice explained Part 2 — Training
- Article: Hacker's Guide to Fundamental Machine Learning Algorithms with Python
- Article: Are Deep Neural Networks Dramatically Overfitted?
- Article: Attention? Attention!
- Article: How to Explain the Prediction of a Machine Learning Model?
- Article: Neural Network from scratch-part 1
- Article: Neural Network from scratch-part 2
- Article: Explain Neural Arithmetic Logic Units (NALU)
- Article: Predict Bitcoin price with Long sort term memory Networks (LSTM)
- Article: Graph Neural Networks - An overview
- Article: Deep Learning Algorithms - The Complete Guide
- AWS: Semantic Segmentation Explained
- AWS: The Elements of Data Science
- AWS: Understanding Neural Networks
- Book: Pattern Recognition and Machine Learning
- Coursera: Neural Networks and Deep Learning
- Datacamp: AI Fundamentals
- Datacamp: Kaggle Competition
- Datacamp: Extreme Gradient Boosting with XGBoost
- Datacamp: Introduction to PySpark
- Datacamp: Building Recommendation Engines with PySpark
- Datacamp: Foundations of Predictive Analytics in Python (Part 1)
- Datacamp: Foundations of Predictive Analytics in Python (Part 2)
- Datacamp: Ensemble Methods in Python
- Datacamp: HR Analytics in Python: Predicting Employee Churn
- Datacamp: Predicting Customer Churn in Python
- Elements of AI
- edX: Principles of Machine Learning
- edX: Data Science Essentials
- edX: Implementing Predictive Analytics with Spark in Azure HDInsight
- DeepMind: Inefficient Data Efficiency
- DeepMind: DeepMind x UCL | Deep Learning Lecture Series 2020
- Fast.ai: Deep Learning for Coder (2020)
- Google: Launching into Machine Learning
- Book: Grokking Deep Learning
- Book: Make Your Own Neural Network
- MIT: 6.S191: Introduction to Deep Learning
- Pluralsight: Understanding Algorithms for Recommendation Systems
- Pluralsight: Deep Learning: The Big Picture
- StatQuest: Machine Learning
- A Gentle Introduction to Machine Learning
0:12:45
- Machine Learning Fundamentals: Cross Validation
0:06:04
- Machine Learning Fundamentals: The Confusion Matrix
0:07:12
- Machine Learning Fundamentals: Sensitivity and Specificity
0:11:46
- Machine Learning Fundamentals: Bias and Variance
0:06:36
- ROC and AUC, Clearly Explained!
0:16:26
- StatQuest: Fitting a line to data, aka least squares, aka linear regression.
0:09:21
- StatQuest: Linear Models Pt.1 - Linear Regression
0:27:26
- StatQuest: Odds and Log(Odds), Clearly Explained!!!
0:11:30
- StatQuest: Odds Ratios and Log(Odds Ratios), Clearly Explained!!!
0:16:20
- StatQuest: Logistic Regression
0:08:47
- Logistic Regression Details Pt1: Coefficients
0:19:02
- Logistic Regression Details Pt 2: Maximum Likelihood
0:10:23
- Logistic Regression Details Pt 3: R-squared and p-value
0:15:25
- Saturated Models and Deviance
0:18:39
- Deviance Residuals
0:06:18
- Regularization Part 1: Ridge (L2) Regression
0:20:26
- Regularization Part 2: Lasso (L1) Regression
0:08:19
- Ridge vs Lasso Regression, Visualized!!!
0:09:05
- Regularization Part 3: Elastic Net Regression
0:05:19
- StatQuest: Principal Component Analysis (PCA), Step-by-Step
0:21:57
- StatQuest: PCA main ideas in only 5 minutes!!!
0:06:04
- StatQuest: PCA - Practical Tips
0:08:19
- StatQuest: PCA in Python
0:11:37
- StatQuest: Linear Discriminant Analysis (LDA) clearly explained.
0:15:12
- StatQuest: MDS and PCoA
0:08:18
- StatQuest: t-SNE, Clearly Explained
0:11:47
- StatQuest: Hierarchical Clustering
0:11:19
- StatQuest: K-means clustering
0:08:57
- StatQuest: K-nearest neighbors, Clearly Explained
0:05:30
- Naive Bayes, Clearly Explained!!!
0:15:12
- Gaussian Naive Bayes, Clearly Explained!!!
0:09:41
- StatQuest: Decision Trees
0:17:22
- StatQuest: Decision Trees, Part 2 - Feature Selection and Missing Data
0:05:16
- Regression Trees, Clearly Explained!!!
0:22:33
- How to Prune Regression Trees, Clearly Explained!!!
0:16:15
- StatQuest: Random Forests Part 1 - Building, Using and Evaluating
0:09:54
- StatQuest: Random Forests Part 2: Missing data and clustering
0:11:53
- The Chain Rule
0:18:23
- Gradient Descent, Step-by-Step
0:23:54
- Stochastic Gradient Descent, Clearly Explained!!!
0:10:53
- AdaBoost, Clearly Explained
0:20:54
- Gradient Boost Part 1: Regression Main Ideas
0:15:52
- Gradient Boost Part 2: Regression Details
0:26:45
- Gradient Boost Part 3: Classification
0:17:02
- Gradient Boost Part 4: Classification Details
0:36:59
- Bam!!! Clearly Explained!!!
0:02:49
- Support Vector Machines, Clearly Explained!!!
0:20:32
- Support Vector Machines Part 2: The Polynomial Kernel
0:07:15
- Support Vector Machines Part 3: The Radial (RBF) Kernel
0:15:52
- XGBoost Part 1: Regression
0:25:46
- XGBoost Part 2: Classification
0:25:17
- XGBoost Part 3: Mathematical Details
0:27:24
- XGBoost Part 4: Crazy Cool Optimizations
0:24:27
- StatQuest: Fiitting a curve to data, aka lowess, aka loess
0:10:10
- Statistics Fundamentals: Population Parameters
0:14:31
- Principal Component Analysis (PCA) clearly explained (2015)
0:20:16
- Decision Trees in Python from Start to Finish
1:06:23
- Udacity: A Friendly Introduction to Machine Learning
- Udacity: Intro to Data Analysis
- Udacity: Intro to Data Science
- Udacity: Intro to Machine Learning
- Udacity: Reinforcement Learning
- Udacity: Deep Learning
- Udacity: Intro to Artificial Intelligence
- Udacity: Classification Models
- Youtube: DETR: End-to-End Object Detection with Transformers (Paper Explained)
- Youtube: Sebastian Ruder: Neural Semi-supervised Learning under Domain Shift
- Youtube: How do we check if a neural network has learned a specific phenomenon?
- Youtube: What is Adversarial Machine Learning and what to do about it? – Adversarial example compilation
- Youtube: AI fabricates music in a celebrity's voice (JukeboxAI)
0:15:54
- Youtube: Activation Functions - EXPLAINED!
0:10:05
- Youtube: Batch Normalization - EXPLAINED!
0:08:48
- Youtube: Optimizers - EXPLAINED!
0:07:22
- Youtube: Loss Functions - EXPLAINED!
0:08:30
- Youtube: Boosting - EXPLAINED!
0:17:31
- Youtube: Gradient Descent - THE MATH YOU SHOULD KNOW
0:20:08
- Youtube: Logistic Regression - VISUALIZED!
0:18:31
- Youtube: Linear Regression and Multiple Regression
0:12:54
- Youtube: Precision, Recall & F-Measure
0:13:42
- Youtube: Bootstrapping, Bagging and Random Forests
0:21:45
- Youtube: Deep Mind's AlphaGo Zero - EXPLAINED
0:11:13
- Youtube: Curiosity in AI
0:06:16
- Youtube: DropBlock - A BETTER DROPOUT for Neural Networks
0:07:45
- Youtube: Neural Voice Cloning
0:19:56
- Youtube: Neural Networks from Scratch in Python
- Youtube: Visualizing Deep Learning
- Youtube: Deep Double Descent
Be able to implement models in scikit-learn
Be able to implement models in Tensorflow and Keras
Be able to implement models in PyTorch
Be able to apply unsupervised learning algorithms
Be able to implement computer vision models
- Article: What is Focal Loss and when should you use it?
- Article: Squeeze and Excitation Networks Explained with PyTorch Implementation
- Article: DenseNet Architecture Explained with PyTorch Implementation from TorchVision
- Article: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Article: Group Normalization
- Article: A Short Introduction to Generative Adversarial Networks
- Article: Semi-supervised Learning with GANs
- Article: Densely Connected Convolutional Networks in Tensorflow
- Article: Convolutional neural networks
- Article: Common architectures in convolutional neural networks
- Article: An overview of semantic image segmentation
- Article: Evaluating image segmentation models
- Article: An overview of object detection: one-stage methods
- Article: A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN
- Article: Object Detection for Dummies Part 1: Gradient Vector, HOG, and SS
- Article: Object Detection for Dummies Part 2: CNN, DPM and Overfeat
- Article: Object Detection for Dummies Part 3: R-CNN Family
- Article: Understanding coordinate systems and DICOM for deep learning medical image analysis
- Article: Understanding the receptive field of deep convolutional networks
- Article: Deep learning in medical imaging - 3D medical image segmentation with PyTorch
- Article: Intuitive Explanation of Skip Connections in Deep Learning
- Article: Human Pose Estimation
- Article: YOLO - You only look once (Single shot detectors)
- Article: Localization and Object Detection with Deep Learning
- Article: Semantic Segmentation in the era of Neural Networks
- Article: ECCV 2020: Some Highlights
- Book: Deep Learning for Computer Vision with Python
- Book: Practical Python and OpenCV
- Coursera: Convolutional Neural Networks
- Datacamp: Biomedical Image Analysis in Python
- Datacamp: Image Processing in Python
- Google: ML Practicum: Image Classification
- Stanford: CS231N Winter 2016
- CS231n Winter 2016: Lecture 1: Introduction and Historical Context
1:19:08
- CS231n Winter 2016: Lecture 2: Data-driven approach, kNN, Linear Classification 1
0:57:28
- CS231n Winter 2016: Lecture 3: Linear Classification 2, Optimization
1:11:23
- CS231n Winter 2016: Lecture 4: Backpropagation, Neural Networks 1
1:19:38
- CS231n Winter 2016: Lecture 5: Neural Networks Part 2
1:18:37
- CS231n Winter 2016: Lecture 6: Neural Networks Part 3 / Intro to ConvNets
1:09:35
- CS231n Winter 2016: Lecture 7: Convolutional Neural Networks
1:19:01
- CS231n Winter 2016: Lecture 8: Localization and Detection
1:04:57
- CS231n Winter 2016: Lecture 9: Visualization, Deep Dream, Neural Style, Adversarial Examples
1:18:20
- CS231n Winter 2016: Lecture 10: Recurrent Neural Networks, Image Captioning, LSTM
1:09:54
- CS231n Winter 2016: Lecture 11: ConvNets in practice
1:15:03
- CS231n Winter 2016: Lecture 12: Deep Learning libraries
1:21:06
- CS231n Winter 2016: Lecture 14: Videos and Unsupervised Learning
1:17:36
- CS231n Winter 2016: Lecture 13: Segmentation, soft attention, spatial transformers
1:10:59
- CS231n Winter 2016: Lecture 15: Invited Talk by Jeff Dean
1:14:49
- Udacity: Introduction to Computer Vision
- Youtube: Deep Residual Learning for Image Recognition (Paper Explained)
- Youtube: Implementing ResNet from scratch
- Youtube: ConvNets Scaled Efficiently
0:13:19
- Youtube: Building an Image Captioner with Neural Networks
0:12:54
- Youtube: Evolution of Face Generation | Evolution of GANs
0:12:23
- Youtube: Autoencoders - EXPLAINED
0:10:53
- Youtube: Unpaired Image-Image Translation using CycleGANs
0:16:22
- Youtube: AI creates Image Classifiers…by DRAWING?
0:09:04
- Youtube: The Evolution of Convolution Neural Networks
0:24:02
- Youtube: Depthwise Separable Convolution - A FASTER CONVOLUTION!
0:12:43
- Youtube: Mask Region based Convolution Neural Networks - EXPLAINED!
0:09:34
- Youtube: Sound play with Convolution Neural Networks
0:11:57
- Youtube: Convolution Neural Networks - EXPLAINED
0:19:20
- Youtube: Generative Adversarial Networks - FUTURISTIC & FUN AI !
0:14:20
Be able to implement NLP models
Be able to model graphs and network data
Be able to implement models for timeseries and forecasting
Be familiar with Reinforcement Learning
Be able to use managed ML services on the cloud
Be able to optimize performance metric
Be able to optimize models for production
Be able to deploy model to production
Be able to perform A/B testing
Be able to write unit tests
Be proficient in Python
Be familiar with compiled languages
Have a general understanding of other parts of the stack
Be familiar with fundamental Computer Science concepts
Be able to apply proper software engineering process
Be able to efficiently use a text editor
Be able to communicate and collaborate well
Be familiar with the hiring pipeline
Broaden Perspective