JuliaDiff / JuliaDiff/ReverseDiff.jl
Programmatically defining the model
Nobody has claimed this yet.
- Dominant language
- Julia
- Stars
- 393
- Forks
- 60
- Avg merge
- 18h 24m
- Merged PRs (30d)
- 8
Description
I'm finding the MNIST example on the MNIST branch very insightful.
In the example, the structure of model is hardcoded. What is the best way, in the ReverseDiff framework, to programmatically define the structure? For example, if I wanted the user to be able to specify at runtime the number of hidden layers and the size and activation functions of each.
Thanks!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the MNIST branch example and inspect where the model structure is hardcoded. Determine how a runtime-specified number of hidden layers, layer sizes, and activation functions could be represented in ReverseDiff; done would be a documented or demonstrated approach for defining that model programmatically.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100