aga

The first of a short series by Welch Labs on building a complete neural network in Python. It introduces the data and the architecture of a simple network before later parts cover forward propagation, gradient descent, and backpropagation.

Martin Gorner's Devoxx talk introduces deep learning with TensorFlow, walking through neural networks for MNIST, how to choose an architecture and how to diagnose networks that fail to train.

The first episode of Google's Machine Learning Recipes series. It introduces machine learning and builds a first supervised-learning classifier in about six lines of Python using scikit-learn.

The Thought Emporium shows how to receive clear images directly from GOES-15, 16 and 17 and Himawari 8 geostationary weather satellites with software-defined radio. It covers the extra effort needed to receive GOES data.

Applied Science builds a replica Apollo DSKY using an electroluminescent driver circuit and screen-printed conductive ink, with source and PCB files published.

Dave Jones of EEVblog and Richard Stephenson tour the 70m DSS43 dish at the Canberra Deep Space Communication Complex and explain how NASA talks to Voyager 2. It covers the transmitters, receivers and tracking involved.

A University of Michigan Medicine demonstration of building a cheap DIY air purifier from a box fan and a HEPA or high-MERV filter using hardware-store parts. It explains why this helps against dust, smoke and viruses and ties it to local air quality readings.

Marco Baringer's tutorial video on SLIME, the Emacs mode for developing Common Lisp. It demonstrates the interactive workflow of working against a live Lisp image.