-
I'm trying out AlignedUMAP for some time-series data but I've run into a weird issue. I have 9 total embeddings - the first 8 of which seem relatively normal but the last of which is very strange. The…
-
Hi @patrick-kidger, as promised I wanted to help improve some of the optimisation methods in optimistix. I'd like to start with the LM implementation.
## Trust region acceptance
The implemented …
-
_source: [Preference Tuning LLMs with Direct Preference Optimization Methods_](https://huggingface.co/blog/pref-tuning)_
-
yes, constant PSF! This proves that at constant PSF, The Thresher returns the image stack.
-
Hi James, similar to #107, I implemented a test to check if `cca_zoo.models.GRCCA` gives similar results as the original implementation. But the feature weights are quite dissimilar especially for the…
-
# Goal
One of the latest/best regularisation techniques for training RBMs is dropout. Unfortunately, the original Boltzmann.jl package does not implement this technique, so we should undertake this o…
-
Hi,
I am interested in understanding the cost to go function across a broad range of different states, not just on chain.
With the default forward pass we end up only exploring the state space…
-
Unknown mat file type, version 54, 48 error thrown while loading the 2D dataset (data. mat). Also, this file is not opening with MatLab.
-
I know it's weird and that somebody should have noticed, but regularization only seems to help when I override the defaut settings and use negative values. With negative values, regularization indeed …
-
It's a great job!!! When I run the cmd, python NIPS_figures.py --data artificial --save_dir layer1, an error happened like below, I wonder how to solve.
Traceback (most recent call last):
File "…