Downloads · 30 days
0
neural-process-pocket
ARotting/neural-process-pocket
neural-process-pocket is a machine learning model from ARotting. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Neural Process Pocket is a Conditional Neural Process trained across a distribution of sine functions. Five unordered context observations are encoded into a task representation; a probabilistic decoder predicts the m…
Access
Public
Updated Jul 30, 2026
Parameters
12.9K
52.2 KB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors52.2 KB · 78%
At a glance
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- 0fc8fd17
Model card
From the Hugging Face model README
Neural Process Pocket
Neural Process Pocket is a Conditional Neural Process trained across a distribution of sine functions. Five unordered context observations are encoded into a task representation; a probabilistic decoder predicts the mean and standard deviation at arbitrary target coordinates.
Evaluation covers RMSE, Gaussian negative log likelihood, and empirical 90% interval coverage on unseen functions. A fixed-kernel RBF Gaussian Process is the non-neural few-shot control.
Verified local result
The 12,866-parameter CNP reached 1.093 RMSE, 1.242 Gaussian NLL, and 88.76% coverage for nominal 90% intervals across 500 unseen five-context-point tasks. The fixed-kernel Gaussian Process reached 1.259 RMSE, 1.328 NLL, and 73.63% coverage.
uv run python projects/neural-process-pocket/train.py
uv run pytest tests/test_neural_process_pocket.py
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026