miniblog.

I loved playing Creatures 3, an ancient game (1999) with some basic neural nets. I'm surprised that ML isn't a bigger deal in virtual pets today!

An optimistic take on neural networks for programming: https://medium.com/@karpathy/software-2-0-a64152b37c35 It makes some good points about predictable runtime performance, ability to trade CPU for accuracy, and the ease of hardware acceleration.

Using machine learning to decide what structure to use for your neural net: https://arxiv.org/pdf/1703.01041.pdf It's pretty meta, but ML is often good at trading computation for results.