General Mathematical Operators

BrainPy Array

Array	Multiple-dimensional array in BrainPy.
ShardedArray	The sharded array, which stores data across multiple devices.

Array Interoperability to JAX

as_device_array	Convert the input to a jax.numpy.DeviceArray.
as_jax	Convert the input to a jax.numpy.DeviceArray.

Array Interoperability to NumPy

as_ndarray	Convert the input to a numpy.ndarray.
as_numpy	Convert the input to a numpy.ndarray.

Array Interoperability to BrainPy

as_variable	Convert the input to a brainpy.math.Variable.
asarray

Activation Functions

celu	Continuously-differentiable exponential linear unit activation.
elu	Exponential linear unit activation function.
gelu	Gaussian error linear unit activation function.
glu	Gated linear unit activation function.
prelu	Applies the element-wise function:
silu	SiLU activation function.
selu	Scaled exponential linear unit activation.
relu
relu6	Rectified Linear Unit 6 activation function.
rrelu	Applies the randomized leaky rectified liner unit function, element-wise, as described in the paper:
hard_silu	Hard SiLU activation function
leaky_relu	Leaky rectified linear unit activation function.
hard_tanh	Hard \(\mathrm{tanh}\) activation function.
hard_sigmoid	Hard Sigmoid activation function.
tanh_shrink	Applies the element-wise function:
hard_swish	Hard SiLU activation function
hard_shrink	Applies the Hard Shrinkage (Hardshrink) function element-wise.
soft_sign	Soft-sign activation function.
soft_shrink	Applies the soft shrinkage function elementwise:
softmax	Softmax function.
softmin	Applies the Softmin function to an n-dimensional input Tensor rescaling them so that the elements of the n-dimensional output Tensor lie in the range [0, 1] and sum to 1.
softplus	Softplus activation function.
swish	SiLU activation function.
mish	Applies the Mish function, element-wise.
log_sigmoid	Log-sigmoid activation function.
log_softmax	Log-Softmax function.
one_hot	One-hot encodes the given indicies.
normalize	Normalizes an array by subtracting mean and dividing by sqrt(var).
sigmoid	Sigmoid activation function.
identity
tanh	Similar to jax.numpy.tanh function, while it is compatible with brainpy Array/Variable.