Building a neural network from scratch in Haskell
www-cs-students.stanford.edu
Building a neural network from scratch in Haskell
1–10 of 38 posts
Re: Building a neural network from scratch in Haskell
#2played with this for ~5 mins and it's insanely bad (maybe it "guessed" right 3/15 tries?) i.e. slightly better than random guesses, even with very clear handwriting :(
Re: Building a neural network from scratch in Haskell
#3Not really my scene, but I've been liking the look of Torsten Scholak's Hasktorch:
Re: Building a neural network from scratch in Haskell
#4In typescript (from scratch recognizing hand-written digits in browser):
Live: https://deep-learning.stackblitz.io/
Live edit code: https://stackblitz.com/edit/deep-learning
Re: Building a neural network from scratch in Haskell
#5All these building NNs in haskell, ocaml or another language solving an extremely simple problem which is ok if you want to just have some fun. But if the proponents are really serious they would put out a detailed tutorial solving a complex task (e.g building a state-of-the-art language model) showing the ease / difficulty of the process, and how using a typed functional language helps in debugging the model - which is supposed to be the biggest selling point of these languages? This will also show whether it is viable for a real life practitioner to invest time in learning these languages / frameworks.
Re: Building a neural network from scratch in Haskell
#6All these building NNs in haskell, ocaml or another language solving an extremely simple problem which is ok if you want to just have some fun. But if the proponents are really serious they would put out a detailed tutorial solving a complex task (e.g building a state-of-the-art language model) showing the ease / difficulty of the process, and how using a typed functional language helps in debugging the model - which…
fast.ai did this with swift in their course https://course.fast.ai/part2
Re: Building a neural network from scratch in Haskell
#7All these building NNs in haskell, ocaml or another language solving an extremely simple problem which is ok if you want to just have some fun. But if the proponents are really serious they would put out a detailed tutorial solving a complex task (e.g building a state-of-the-art language model) showing the ease / difficulty of the process, and how using a typed functional language helps in debugging the model - which…
fast.ai did this with swift in their course https://course.fast.ai/part2
I have been casually playing around with TensorFlow for Swift since it was announced. It shows promise but I question long term support and development.
The Julia language with the Flux deep learning library is another very interesting but not mainstream path to take.
Re: Building a neural network from scratch in Haskell
#8In typescript (from scratch recognizing hand-written digits in browser): Live: https://deep-learning.stackblitz.io/ Live edit code: https://stackblitz.com/edit/deep-learning
Nice. I really recommend that practitioners implement simple neural architectures from scratch for learning, but use TensorFlow, PyTorch, mxnet, etc. for production and serious research.
New frameworks like TensorFlow for Swift and Julia’s Flux are a little easier to understand if you read the code, but still complex stuff.
Re: Building a neural network from scratch in Haskell
#9Not really my scene, but I've been liking the look of Torsten Scholak's Hasktorch: https://github.com/tscholak/hasktorch
I think that Hasktorch is a very cool project but it is not turtles all the way down: it is a Haskell API on top of PyTorch.
The Haskell bindings for TensorFlow are a little bit difficult for me to work with. When HaskTorch gets more mature and stable, it will hopefully be easier to use than the TensorFlow bindings.
Re: Building a neural network from scratch in Haskell
#10All these building NNs in haskell, ocaml or another language solving an extremely simple problem which is ok if you want to just have some fun. But if the proponents are really serious they would put out a detailed tutorial solving a complex task (e.g building a state-of-the-art language model) showing the ease / difficulty of the process, and how using a typed functional language helps in debugging the model - which…
Learning the basics has its place. People have to start somewhere. A tutorial for more complex, real world problems is a totally different thing. Both are interesting in their own ways.