liquid networks

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.

Andrej Karpathy builds a bigram character-level language model from scratch, introducing torch.Tensor and the framework of training, sampling and loss evaluation. It is the first step toward a GPT-style Transformer in his makemore series.

Ben Krasnow of Applied Science shows how to make and test YBCO high-temperature superconductor with a kiln and eBay chemicals. He demonstrates flux pinning and shows a close-up of the crystal structure.

Tech Ingredients shows how to make a homemade radiative cooling paint, with a custom liquid panel that cools below ambient temperature outdoors. The video covers the materials and how to apply the paint.

Tech Ingredients shows how to build a liquid panel with a specialty paint that, placed outside, cools below ambient air temperature. It demonstrates radiative sky cooling.