jax

Feature request

Is the addition of the 'OPTforSequenceClassification' class scheduled?
Is someone handling it?
When adding these functions, I wonder if it is possible to PR one by one, or if I have to PR all classes supported by other models.

Motivation

Added function of OPT class, which is being actively discussed recently

Your contribution

I personally use the forSequenceCla

It would be great if you could add the JAX equivalent of scipy.stats.mode, which is currently unavailable.

A use case may be a ML classification task with ensembles, where multiple models give different predictions, and we are interested in finding the most common one.

As an example, consider predictions to be a two-dimensional DeviceArray of predictions, with
shape = (number of model

Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?

Love the book! Ran into this display issue when viewing it on Chrome's PDF viewer:

Right now, qml.operation.expand_matrix is often called in a code-block like:

if wire_order is None or self.wires == Wires(wire_order):
    return canonical_matrix

expand_matrix(canonical_matrix, wires=self.wires, wire_order=wire_order)

see [pennylane/operation.py Line 587](https://github.com/PennyLaneAI/pennylane/blob/b6fc5380abea6215661704ebe2f5cb8e7a599635/pennylane/operation.p

Hi,

I am trying to use random_flax_module on a class that uses flax.linen.BatchNorm that uses mutable parameters. Is there any example on how to use that? Here is my code:

The model:

class NSBlock(nn.Module):

    train: bool
    dim: int
    ks_1: int = 3
    ks_2: int = 3
    dl_1: int = 1
    dl_2: int = 1
    mp_ks: int = 3
    mp_st: int = 1

    @nn.compact
    def

Dear Brax team,

Since Brax is fully differentiable, I thought it'd be possible to use it like DiffTaichi or GradSim for system identification (e.g. determining the mass of an object from a trajectory and known force) but I couldn't find any example for this.
Do you happen to have any demo or tips for this?

From the top of my head I would do something like this:
Let's say the task is to es