This doesn’t answer your question directly, but I recommend Turing or DynamicHMC, as they are more activity maintained and developed. Turing in particular is geared towards machine learning. You might find some useful information in this thread.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Need help with Mamba.jl :roll_eyes: | 2 | 872 | August 26, 2017 | |
Gradient of neural network parameters used inside of SMC simulation | 4 | 324 | November 9, 2023 | |
Deep Bayesian Model Discovery without using NeuralODE object | 4 | 452 | August 3, 2023 | |
Zygote - parametrize matrix such that gradient is only performed on selected coefficients | 1 | 546 | June 5, 2021 | |
Issues with HMC/NUTS samplers | 4 | 649 | September 29, 2021 |