All Episodes

Re-release: Auto-generating websites with deep learning

Advice to those trying to get a first job in data science

Re - Release: Machine Learning Technical Debt

Estimating Software Projects, and Why It's Hard

The Black Hole Algorithm

Structure in AI

The Great Data Science Specialist vs. Generalist Debate

Google X, and Taking Risks the Smart Way

Statistical Significance in Hypothesis Testing

The Language Model Too Dangerous to Release

The cathedral and the bazaar

AlphaStar

Are machine learning engineers the new data scientists?

Interview with Alex Radovic, particle physicist turned machine learning researcher

K Nearest Neighbors

Not every deep learning paper is great. Is that a problem?

The Assumptions of Ordinary Least Squares

Quantile Regression

Heterogeneous Treatment Effects

Pre-training language models for natural language processing problems

Facial Recognition, Society, and the Law

Re-release: Word2Vec

Re - Release: The Cold Start Problem

Convex (and non-convex) Optimization

The Normal Distribution and the Central Limit Theorem

Software 2.0

Limitations of Deep Nets for Computer Vision

Building Data Science Teams

Optimized Optimized Web Crawling

Optimized Web Crawling

Better Know a Distribution: The Poisson Distribution

Searching for Datasets with Google

It's our fourth birthday

Gigantic Searches in Particle Physics

Data Engineering

Text Analysis for Guessing the NYTimes Op-Ed Author

The Three Types of Data Scientists, and What They Actually Do

Agile Development for Data Scientists, Part 2: Where Modifications Help

Agile Development for Data Scientists, Part 1: The Good

Re - Release: How To Lose At Kaggle

Troubling Trends In Machine Learning Scholarship

Can Fancy Running Shoes Cause You To Run Faster?

Compliance Bias

AI Winter

Rerelease: How to Find New Things to Learn

Rerelease: Space Codes

Rerelease: Anscombe's Quartet

Rerelease: Hurricanes Produced

GDPR

Git for Data Scientists

Analytics Maturity

SHAP: Shapley Values in Machine Learning

Game Theory for Model Interpretability: Shapley Values

AutoML

CPUs, GPUs, TPUs: Hardware for Deep Learning

A Technical Introduction to Capsule Networks

A Conceptual Introduction to Capsule Networks

Convolutional Neural Nets

Google Flu Trends

How to pick projects for a professional data science team

Autoencoders

When Private Data Isn't Private Anymore

What makes a machine learning algorithm "superhuman"?

Open Data and Open Science

Defining the quality of a machine learning production system

Auto-generating websites with deep learning

The Case for Learned Index Structures, Part 2: Hash Maps and Bloom Filters

The Case for Learned Index Structures, Part 1: B-Trees

Challenges with Using Machine Learning to Classify Chest X-Rays

The Fourier Transform

Statistics of Beer

Re - Release: Random Kanye

Debiasing Word Embeddings

The Kernel Trick and Support Vector Machines

Maximal Margin Classifiers

Re - Release: The Cocktail Party Problem

Clustering with DBSCAN

The Kaggle Survey on Data Science

Machine Learning: The High Interest Credit Card of Technical Debt

Improving Upon a First-Draft Data Science Analysis

Survey Raking

Happy Hacktoberfest

Re - Release: Kalman Runners

Neural Net Dropout

Disciplined Data Science

Hurricane Forecasting

Finding Spy Planes with Machine Learning

Data Provenance

Adversarial Examples

Jupyter Notebooks

Curing Cancer with Machine Learning is Super Hard

KL Divergence

Sabermetrics

What Data Scientists Can Learn from Software Engineers

Software Engineering to Data Science

Re-Release: Fighting Cholera with Data, 1854

Re-Release: Data Mining Enron

Factorization Machines

Anscombe's Quartet

Traffic Metering Algorithms