deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN Class Reference

Inheritance diagram for deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN:

Public Member Functions
None	__init__ (self, *Layer|Activation architecture, tuple[int, int, int] input_shape, Optional[int] batch_size=None)
None	configure (self, float learning_rate=1e-6, float inference_rate=0.1, float lmbda=1e-2, str optimizer="SGD")
None	set_learning_rate (self, float lr)
None	set_inference_rate (self, float ir)
None	set_lambda (self, float lmbda)
None	set_optimizer (self, str optimizer)
float	train_step (self, npt.NDArray[np.float32] X, npt.NDArray[np.float32] Y, int steps)
npt.NDArray[np.float32]	predict (self, npt.NDArray[np.float32] X, int steps)
float	train_step_with_projection (self, npt.NDArray[np.float32] X, npt.NDArray[np.float32] Y, int steps)
npt.NDArray[np.float32]	predict_with_projection (self, npt.NDArray[np.float32] X, int steps)
"SimpleConvolutionalPCN"	fit (self, npt.NDArray[np.float32] X, npt.NDArray[np.float32] Y, int epochs, int steps, Optional[float] initial_lr=None, float decay_rate=1.0, bool shuffle=True)

Public Attributes
	architecture = architecture
	input_shape = input_shape
	layers

Protected Member Functions
None	_validate_architecture (self)
None	_build_backend (self)
None	_require_configured (self)

Protected Attributes
Optional[float]	_learning_rate = None
Optional[float]	_inference_rate = None
Optional[float]	_lambda = None
Optional[str]	_optimizer = None
bool	_configured = False

Detailed Description

Simple convolutional Predictive Coding Network.

The architecture is declared using Convolution and Activation objects,
while optimization and inference parameters are supplied through
configure().

Constructor & Destructor Documentation

__init__()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.__init__	(		self,
		*Layer | Activation	architecture,
		tuple[int, int, int]	input_shape,
		Optional[int]	batch_size = None )

Member Function Documentation

_build_backend()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._build_backend ( self )

protected

_require_configured()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._require_configured ( self )

protected

_validate_architecture()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._validate_architecture ( self )

protected

configure()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.configure	(		self,
		float	learning_rate = 1e-6,
		float	inference_rate = 0.1,
		float	lmbda = 1e-2,
		str	optimizer = "SGD" )

Configure network hyperparameters and initialize the backend.
Must be called once, before train_step()/predict().

@param learning_rate Learning rate for the forward weights.
@param inference_rate Inference/settling rate.
@param lmbda Regularization parameter.
@param optimizer Optimizer used for the forward weights.

fit()

"SimpleConvolutionalPCN" deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.fit	(		self,
		npt.NDArray[np.float32]	X,
		npt.NDArray[np.float32]	Y,
		int	epochs,
		int	steps,
		Optional[float]	initial_lr = None,
		float	decay_rate = 1.0,
		bool	shuffle = True )

Train for multiple epochs over (X, Y), batching by
`self.batch_size` and printing a progress bar.

predict()

npt.NDArray[np.float32] deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.predict	(		self,
		npt.NDArray[np.float32]	X,
		int	steps )

Run inference on `X`, settling for `steps` iterations.
@return The terminal layer's beliefs.

predict_with_projection()

npt.NDArray[np.float32] deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.predict_with_projection	(		self,
		npt.NDArray[np.float32]	X,
		int	steps )

Same as predict(), but initializes every layer's beliefs
via a forward projection pass first.

set_inference_rate()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.set_inference_rate	(		self,
		float	ir )

Set the inference/settling rate on every layer.

set_lambda()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.set_lambda	(		self,
		float	lmbda )

Set the regularization parameter on every layer.

set_learning_rate()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.set_learning_rate	(		self,
		float	lr )

Set the learning rate on every layer.

set_optimizer()

None deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.set_optimizer	(		self,
		str	optimizer )

Set the optimizer used for the forward weights.

train_step()

float deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.train_step	(		self,
		npt.NDArray[np.float32]	X,
		npt.NDArray[np.float32]	Y,
		int	steps )

Run one training step on a single batch, settling for
`steps` iterations before updating weights.
@return Total settling energy accumulated over `steps`.

train_step_with_projection()

float deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.train_step_with_projection	(		self,
		npt.NDArray[np.float32]	X,
		npt.NDArray[np.float32]	Y,
		int	steps )

Same as train_step(), but initializes every layer's
beliefs via a forward projection pass first.

Member Data Documentation

_configured

bool deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._configured = False

protected

_inference_rate

Optional[float] deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._inference_rate = None

protected

_lambda

Optional[float] deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._lambda = None

protected

_learning_rate

Optional[float] deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._learning_rate = None

protected

_optimizer

Optional[str] deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN._optimizer = None

protected

architecture

deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.architecture = architecture

input_shape

deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.input_shape = input_shape

layers

deepity.SimpleConvolutionalPCN.SimpleConvolutionalPCN.layers

---

The documentation for this class was generated from the following file:

• deepity/SimpleConvolutionalPCN.py