Alternatives
Products that do what I trained a neural network to write Kanji does
- 1IT
2018 · github.com
- 2IW
2017 · github.com
- 3NJ
2017 · github.com
- 4IM
2021 · pinecone.io
- 5TB
2017 · github.com
- 6

- 7AT
2019 · github.com
- 8

- 9NN
2020 · github.com
- 10IT
2020 · github.com
- 11IT
2021 · github.com
- 12GR
2020 · calligrapher.ai
- 13IB
Apr 2026 · doudou-chinese.com
- 14IB
2020 · dip-lang.org
- 15NN
2016 · otoro.net
- 16NN
2015 · github.com
- 17IB
2021 · codigo.so
- 18AA
2018 · play.google.com
- 19IC
I spent the past week implementing a 1 Layer Neural Net and training it on MNIST within the visual scripting language provided by scratch.mit.edu. It was tedious, but ultimately not too difficult. The code runs incredibly slowly, so much so that 64 samples of MNIST takes 5+ hours to train on my machine. There were a lot of little mini challenges that were fun to overcome (implementing softmax was very tricky). If you're interested, I encourage you to try and improve on it! More details in the linked blog post.
2024 · bell-boy.github.io
- 20IB
2021 · joeldare.com
- 21IW
2021 · github.com
- 22IM
2016 · octopusnote.com
- 23IM
2020 · vo.codes
- 24IA
2018 · enlight.nyc
Ranked by how close each launch is in meaning, then by votes. Refine with a description →