Producing a Chainsmokers Remix with AI (MusicAutobot), DAWNBench & fast.ai | Interview with Andrew Shaw

Published: Sept. 28, 2019, 6:05 p.m.

In this episode, Sanyam Bhutani interviews Andrew Shaw. In this interview, they talk all about Andrew's journey into the field, his fast.ai journey, and his recent project: musicautobot. MusicAutobot is an "AI Pop Music Generator". They also briefly talk about the fast.ai DAWNBench results.

\n

Links: 

\n

https://musicautobot.com/

\n


\n

fast.ai DAWNBench: https://www.fast.ai/2018/08/10/fastai-diu-imagenet/

\n

https://www.fast.ai/2018/04/30/dawnbench-fastai/

\n

Blogposts:

\n

Part 1: https://towardsdatascience.com/creating-a-pop-music-generator-with-the-transformer-5867511b382a

\n

Part 2: https://towardsdatascience.com/practical-tips-for-training-a-music-model-755c62560ec2

\n

Part 3: https://towardsdatascience.com/a-multitask-music-model-with-bert-transformer-xl-and-seq2seq-3d80bd2ea08e

\n

Part 4: https://towardsdatascience.com/how-to-remix-the-chainsmokers-with-a-music-bot-6b920359248c

\n


\n

Follow:

\n

Andrew Shaw:

\n

https://twitter.com/bearpelican

\n


\n

Sanyam Bhutani:

\n

https://twitter.com/bhutanisanyam1

\n

Blog: https://medium.com/@init_27

\n


\n

About:

\n

http://chaitimedatascience.com/

\n

A show for Interviews with Practitioners, Kagglers & Researchers and all things Data Science hosted by Sanyam Bhutani. 

\n


\n

You can expect weekly episodes every available as Video, Podcast, and blogposts.

\n


\n

If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience