Neural Networks, Types, and Functional Programming -- colah's blog

Posted on September 3, 2015 Deep learning, despite its remarkable successes, is a young field. While models called artificial neural networks have been studied for decades, much of that work seems only tenuously connected to modern results. It’s often the case that young fields start in a very ad-hoc manner. Later, the mature field is understood very differently than it was understood by its early practitioners. For example, in taxonomy, people have grouped plants and animals for thousands of

2 mentions: @MilesCranmer@austinvhuang
Date: 2021/01/13 18:53

Referring Tweets

@MilesCranmer Also, shout out to @ch402 for his many amazing blogs on neural nets. This paragraph from in particular has been inspiring for this work. I think viewing deep learning as flexible functional programming helps quite a bit with crafting new inductive biases!
@austinvhuang Thanks for the @hasktorch shout out from the top of HN @marksaroufim. 💯% agree on the connection between FP and NNs. I always thought @ch402 articulated it well There remains a lot of low hanging fruit to explore connecting types, FP, and NNs.

Related Entries

Read more Akitoshi Takayasu(高安亮紀)-Homepage-
0 users, 1 mentions 2021/01/04 21:51
Read more 2020年振り返りと2021年の目標(データサイエンティストとしてのnikkie編) - nikkie-ftnextの日記
0 users, 1 mentions 2021/01/05 12:30
Read more 最適輸送の計算アルゴリズムの研究動向
1 users, 0 mentions 2021/01/10 09:50
Read more Google AI Blog: Google Research: Looking Back at 2020, and Forward to 2021
0 users, 7 mentions 2021/01/12 21:51
Read more Google AI Blog: Federated Learning: Collaborative Machine Learning without Centralized Training Data
0 users, 0 mentions 2021/01/13 11:21