Package dimer :: Package nnet :: Module nccn :: Class LogisticReg

Class LogisticReg

object --+        
         |        
     Layer --+    
             |    
    SpeedLayer --+
                 |
                LogisticReg

A logistic regression layer

Nested Classes

[hide private]

Inherited from Layer: __metaclass__

Instance Methods

[hide private]

__init__(self, X, n_in, n_out, rng, dtype)
A logistic regression layer

source code

activation(self)
softmax activation.

source code

__str__(self)
str(x)

source code

Inherited from SpeedLayer: get_params, get_speeds, set_params, set_speeds, speed_update, weight_update

Inherited from Layer: get_flat_weights, get_weights, load_flat_weights, set_weights, weight_norm

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __subclasshook__

Class Methods

[hide private]

Inherited from SpeedLayer (private): _speed_update_f, _weight_update_f

Class Variables

[hide private]

__abstractmethods__ = frozenset([])

Inherited from Layer (private): _abc_cache, _abc_negative_cache, _abc_negative_cache_version, _abc_registry

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

init(self, X, n_in, n_out, rng, dtype)
(Constructor)

source code

A logistic regression layer

the layer has a weight and a bias matrix as weights and parameters.

Parameters:

wshape_lst - shapes of weights
wnames - names of weights
fanin_lst - fan in of weights
rng - a random number generator or init value (see alloc_shared_weights_)
wdtype - data type of weights.

Overrides: object.__init__

activation(self)

source code

softmax activation. XW + b (samples are rows)

Overrides: Layer.activation

str(self)
(Informal representation operator)

source code

str(x)

Overrides: object.__str__: (inherited documentation)

Class LogisticReg

__init__(self, X, n_in, n_out, rng, dtype) (Constructor)

activation(self)

__str__(self) (Informal representation operator)

init(self, X, n_in, n_out, rng, dtype)
(Constructor)

str(self)
(Informal representation operator)