Custom output such as exponential function?
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 20/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- julia
- Domain
- machine-learning
Research direction
The issue concerns using an exponential activation for the last layer, with output exp(w*x + b). No files, tests, or entry points are mentioned, so begin by locating the package's last-layer and activation-function APIs. Done would require either a documented supported approach or a clearly scoped implementation plan for custom activations.
Written by the indexing model from the issue text.
Description
Hi there,
I am trying to define the activation of the last layer as the exponential function. If x is the input vector to a node in the last layer, the output of the node would be exp(w*x + b). Is this possible?
Thanks!
Jock
- Dominant language
- No language data
- Stars
- 370
- Forks
- 63
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
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.
More from dmlc/MXNet.jl
-
Import fail MXNET.jlOpen
Difficulty 3/5 1-2 days Newbie friendliness 28/100
-
Difficulty 4/5 3-5 days Newbie friendliness 30/100
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Nixtla/mlforecast#823 ·
Maintainers usually reply within 1 day
-
IFEvalG exclude_word_harder misses the keyword next to punctuation, at the start or end of the text, and in other letter casePossibly taken @damienen claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
allenai/open-instruct#2151 ·
Maintainers usually reply within 1 day
-
NemotronH: float32 identity weight in gated RMSNorm makes all activations float32 (~3x slower decode)Possibly taken @Augustas11 claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
ml-explore/mlx-swift-lm#751 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
lightseekorg/TorchSpec#206 ·
-
Unmasked swiglu/geglu fwd and bwd kernels index rows in int32: illegal memory access once M * stride(0) >= 2^31Possibly taken @jbelofamd claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
AMD-AGI/Primus-Turbo#593 ·
Maintainers usually reply within 1 day