Alternatives
Products that do what SpaCy v2 alpha. New 15MB neural model, multi-language NER, training API does
- 1TA
2020 · thinc.ai
- 2LO
2021 · libretranslate.com
- 3LA
2021 · lunarvim.org
- 4N5
2020 · nn-512.com
- 5

- 6NN
2020 · github.com
- 7NJ
2017 · github.com
- 8

- 9SN
2020 · github.com
- 10AV
2016 · jalammar.github.io
- 11SA
2020 · github.com
- 12CM
2019 · github.com
- 13

- 14LA
2014 · github.com
- 15PA
2017 · github.com
- 16CO
2020 · github.com
- 17PA
2019 · panini.ai
- 18NU
2020 · github.com
- 19AG
2017 · github.com
- 20FD
2014 · github.com
- 21AF
2016 · openapi.keplr.io
- 22AF
2017 · github.com
- 23RB
2014 · github.com
- 24IC
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
Ranked by how close each launch is in meaning, then by votes. Refine with a description →