Malt: A Deep Learning Framework for Racket by Anurag Mendhekar and Daniel P. Friedman(“Lispman”) <a href="https://www.thelittlelearner.com/" rel="nofollow">https://www.thelittlelearner.com/</a><p>> We discuss the design of a deep learning toolkit, Malt (<a href="https://github.com/themetaschemer/malt">https://github.com/themetaschemer/malt</a>), that has been built for Racket. Originally designed to support the pedagogy of [The Little Learner—A Straight Line to Deep Learning](<a href="https://mitpress.mit.edu/9780262546379/the-little-learner/" rel="nofollow">https://mitpress.mit.edu/9780262546379/the-little-learner/</a>), it is used to build deep neural networks with a minimum of fuss using tools like higher-order automatic differentiation and rank polymorphism. The natural, functional style of AI programming that Malt enables can be extended to much larger, practical applications. We present a roadmap for how we hope to achieve this so that it can become a stepping stone to allow Lisp/Scheme/Racket to reclaim the crown of being the language for Artificial Intelligence (perhaps!).<p>Watch <a href="https://youtu.be/AW9isjesTkQ" rel="nofollow">https://youtu.be/AW9isjesTkQ</a>