Skip to content

Commit

Permalink
Update dependencies description
Browse files Browse the repository at this point in the history
  • Loading branch information
francesco-innocenti committed Jun 12, 2024
1 parent 71e14c2 commit c2a20d3
Show file tree
Hide file tree
Showing 2 changed files with 7 additions and 10 deletions.
8 changes: 4 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@ useful JAX transforms such as `vmap` and `jit`.
pip install jpc
```

Requires Python 3.8+, JAX 0.4.13+, [Equinox](https://github.com/patrick-kidger/equinox)
0.10.4+, [Diffrax](https://github.com/patrick-kidger/diffrax) 0.3.1+, and
[Jaxtyping](https://github.com/patrick-kidger/jaxtyping) 0.2.19+.
Requires Python 3.9+, JAX 0.4.23+, [Equinox](https://github.com/patrick-kidger/equinox)
0.11.2+, [Diffrax](https://github.com/patrick-kidger/diffrax) 0.5.1+, and
[Jaxtyping](https://github.com/patrick-kidger/jaxtyping) 0.2.24+.

## Documentation
Available at X.
Expand Down Expand Up @@ -70,4 +70,4 @@ pc_param_grads = jpc.compute_pc_param_grads(
)
```
The gradients can then be fed to your favourite optimiser (e.g. gradient
descent) to update the network parameters.
descent) to update the network parameters.
9 changes: 3 additions & 6 deletions docs/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,17 +11,15 @@ activity (inference) dynamics.
JPC provides a simple but flexible API for research of PCNs compatible with
useful JAX transforms such as `vmap` and `jit`.


## Installation

```
pip install jpc
```

Requires Python 3.8+, JAX 0.4.13+, [Equinox](https://github.com/patrick-kidger/equinox)
0.10.4+, [Diffrax](https://github.com/patrick-kidger/diffrax) 0.3.1+, and
[Jaxtyping](https://github.com/patrick-kidger/jaxtyping) 0.2.19+.

Requires Python 3.9+, JAX 0.4.23+, [Equinox](https://github.com/patrick-kidger/equinox)
0.11.2+, [Diffrax](https://github.com/patrick-kidger/diffrax) 0.5.1+, and
[Jaxtyping](https://github.com/patrick-kidger/jaxtyping) 0.2.24+.

## Quick example

Expand Down Expand Up @@ -70,5 +68,4 @@ pc_param_grads = jpc.compute_pc_param_grads(
The gradients can then be fed to your favourite optimiser (e.g. gradient
descent) to update the network parameters.


## Citation

0 comments on commit c2a20d3

Please sign in to comment.