A Neural Network in 13 lines of Python (Part 2 – Gradient Descent)

Summary: I learn best with toy code that I can play with. This tutorial teaches gradient descent via a very simple toy example, a short python implementation.
Followup Post: I intend to write a followup post to this one adding popular features leveraged by state-of-the-art approaches (likely Dropout, DropConnect, and Momentum). I’ll tweet it out when it’s complete @iamtrask.

Read Full Story

Best practices with pandas (video series)

At the PyCon 2018 conference, I presented a tutorial called “Using pandas for Better (and Worse) Data Science”. Through a series of exercises, I demonstrated best practices with pandas to help students become more fluent at using pandas to answer data science questions and avoid data science errors.
I split the tutorial into 10 videos.

Read Full Story

Web scraping the President’s lies in 16 lines of Python

Note: This tutorial is available as a video series and a Jupyter notebook, and the dataset of lies is available as a CSV file.
Summary
This an introductory tutorial on web scraping in Python. All that is required to follow along is a basic understanding of the Python programming language.

Read Full Story

GPU Powered DeepLearning with NVIDIA DIGITS on EC2

In this tutorial I am going to show you how to set up CUDA 7, cuDNN, caffe and DIGITS on a g2.2xlarge EC2 instance (running Ubuntu 14.04 64 bit) and how to get started with DIGITS. For illustrating DIGITS’ application I use a current Kaggle competition about detecting diabetic retinopathy and its state from fluorescein angiography.

Read Full Story

How to Code and Understand DeepMind’s Neural Stack Machine

Summary: I learn best with toy code that I can play with. This tutorial teaches DeepMind’s Neural Stack machine via a very simple toy example, a short python implementation. I will also explain my thought process along the way for reading and implementing research papers from scratch, which I hope you will find useful.

Read Full Story

LOCF and Linear Imputation with PostgreSQL

This tutorial will introduce various tools offered by PostgreSQL, and SQL in general – like custom functions, window functions, aggregate functions, WITH clause (or CTE for Common Table Expression) – for the purpose of implementing a program which imputes numeric observations within a column applying linear interpolation where possible and forward and backward padding where necessary.

Read Full Story

Deep Time-to-Failure: Predictive maintenance using RNNs and Weibull distributions

I published on GitHub a tutorial on how to implement an algorithm for predictive maintenance using survival analysis theory and gated Recurrent Neural Networks in Keras.
The tutorial is divided into:
Fitting survival distributions and regression survival models using lifelines.

Read Full Story

Adding an E-Commerce Admin Dashboard to Saleor

In this tutorial, we’ll explore how to add analytical features, such as reporting and dashboarding to an existing e-commerce web application with Cube.js. We’re going to use Saleor as our e-commerce platform. It is powered by a GraphQL server running on top of Python 3 and a Django 2 framework.

Read Full Story