Table of Contents

Welcome!
Pour yourself a mug of something hot and have a look around.

Career development

• 000. Foundational skills
• 101. Data science concepts
• 121. Career advice

Tools

• 131. Data munging in Python
• 133. Matplotlib
• 134. Python concepts and cookbooks I: Foundations
• 135. Python concepts and cookbooks II: Advanced topics
• 137. Signal processing

Tutorials

• 171. Choosing a model
• 173. Optimization
• 191. Models and methods
• 193. Neural network concepts

Machine learning case studies

• 201. Python intro: Time tools
• 211. Decision trees
• 212. Time-series analysis
• 213. Polynomial regression
• 221. k-nearest neighbors

End-to-end machine learning projects

• 311. Neural network visualization
• 312. Build a neural network framework
• 313. Advanced neural network methods
• 314. Neural network optimization


• 321. One dimensional convolutional neural networks
• 322. Two dimensional convolutional neural networks

• Cottonwood machine learning framework

Foundational Skills

• 011. Python
• 012. NumPy
• 016. C++
• 021. SQL
• 031. Calculus
• 032. Linear Algebra
• 041. Statistics
• 071. Git
• 081. Machine learning
• 091. Mental Focus
• 111. Getting ready to learn Python, Mac edition
• 112. Getting ready to learn Python, Windows edition

• How data science works
• Data science for beginners
• There is more to data science than machine learning
• What is data
• How to get good quality data
• What questions can machine learning answer

• Data science archetypes
• How to choose a project
• How to solve a hard problem
• How to choose your tools
• Oversimplify your communication
• Decide and commit
• Choose your professional path
• How to get a job you like
• Up-level your resume
• How to get hired as a data scientist
• Get to know your new company
• Imposter syndrome
• Build a strong data science team
• Build a strong distributed data science team
• What to do when a leader does something wrong

• How to slice and index pandas DataFrames
• Reading and writing data files
• Play and record sounds
• Make your code run faster
• How to use datetime
• Turn images to videos and back
• Make your own personal Python toolbox
• Use Multiprocessing

• Quick start guide
• Three important ideas
• Lines and curves
• Scatterplots and points
• Colors and colormaps
• Text, axis labels, and annotation
• Patches
• Ticks, tick labels, and grids
• Layout, background, and multiple plots
• Manual animations

• Data types

• Threading
• Multiprocessing for Parallelization
• Multiprocessing for Real-Time Applications
• Make your code run faster

• How to normalize a signal by its minimum and maximum
• How to normalize a signal by mean and variance
• Rate of change
• Exponential smoothing
• How to turn a picture into numbers
• How to convert RGB color images to grayscale
• One dimensional convolution
• Two dimensional convolution

• Optimization methods
• Optimizing a central tendency model
• Optimizing a linear model
• Optimizing complex models

• Choosing between models
• Separating signal from noise
• Choosing a loss function
• Splitting the data
• Navigating assumptions

• How decision trees work
• How Bayesian inference works
• How convolution works
• How autocorrelation works
• How support vector machines work

• How fully connected neural networks work
• How convolutional neural networks work
• How convolutional neural networks work, in depth
• How recurrent neural networks and LSTM work
• How transformers work
• How backpropagation works
• What neural networks can learn
• Approaching human intelligence through robotics

A Python course for the absolute beginner. Zero prior knowledge assumed. Learn Python basics while building projects like a clock, a timer, and a stopwatch.

• Code up a decision tree in python from scratch.
• Dynamically construct URL queries for live transit data API.
• Build the model into a command line application.

• Build a command line weather prediction tool from a century of data.
• Perform data-driven deseasonalization to remove annual weather patterns.
• Use autocorrelation to extract predicted temperatures.

• Code up a robust optimizer from scratch in python.
• Fit high-order polynomials to real data on dog breeds.
• Implement Monte Carlo cross-validation to select the best model.

• Code up the k-nearest neighbors algorithm in Python.
• Use k-NN for categorization, regression, and interpolation on several data sets.

• Create a custom neural network visualization in python.
• Learn Matplotlib tricks for making professional plots.

• Code up a fully connected deep neural network from scratch in Python.
• Extend it into a framework through object-oriented design.

• Add regularization, dropout, computation graphs and optimizer options to the framework we built in Course 312.
• Run it on images from Mars.
• How Regularization Works

• Build an autoencoder to extract basis elements of images of the Martian surface.
• Optimize compression performance by tuning hyperparameters.
• Build and use Evolutionary Powell's method, an experimental hyperparameter optimization algorithm.

• Build a classification model for detecting unhealthy rhythms in electrocardiography data.
• How one dimensional convolution works
• Electrocardiogram case study

• Build image classification models for benchmark data sets.
• Two dimensional convolution
• Softmax
• Batch normalization
• MNIST digits case study
• CIFAR-10 images case study

• k-nearest neighbors adaptive feature weighting
• k-nearest neightbors data reduction
• k-sparse neural network layer
• Evolutionary Powell's method for hyperparameter tuning
• Pathfinder many-to-many shortest path algorithm
• Publications

• Video walkthrough ( part 1 and part 2).
• Autoencoder for Norse rune compression
• Autoencoder for Martian image compression
• Convolutional neural network for detecting heartbeats
• Convolutional neural network for classifying MNIST digits
• Convolutional neural network for classfying CIFAR-10 images
• Convolutional encoder-decoder for CIFAR-10 images
• k-nearest neighbor classifier for Palmer penguins
• k-nearest neighbor predictor for diamond prices