TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Malt: A Deep Learning Framework for Racket

1 点作者 spdegabrielle10 个月前

1 comment

spdegabrielle10 个月前
Malt: A Deep Learning Framework for Racket by Anurag Mendhekar and Daniel P. Friedman(“Lispman”) <a href="https:&#x2F;&#x2F;www.thelittlelearner.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.thelittlelearner.com&#x2F;</a><p>&gt; We discuss the design of a deep learning toolkit, Malt (<a href="https:&#x2F;&#x2F;github.com&#x2F;themetaschemer&#x2F;malt">https:&#x2F;&#x2F;github.com&#x2F;themetaschemer&#x2F;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:&#x2F;&#x2F;mitpress.mit.edu&#x2F;9780262546379&#x2F;the-little-learner&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mitpress.mit.edu&#x2F;9780262546379&#x2F;the-little-learner&#x2F;</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&#x2F;Scheme&#x2F;Racket to reclaim the crown of being the language for Artificial Intelligence (perhaps!).<p>Watch <a href="https:&#x2F;&#x2F;youtu.be&#x2F;AW9isjesTkQ" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;AW9isjesTkQ</a>