Package topo :: Package projection :: Module basic :: Class OneToOneProjection

Class OneToOneProjection

                       object --+            
                                |            
param.parameterized.Parameterized --+        
                                    |        
         base.simulation.EPConnection --+    
                                        |    
               base.projection.Projection --+
                                            |
                                           OneToOneProjection

A projection that has at most one input connection for each unit.

This projection has exactly one weight for each destination unit. The input locations on the input sheet are determined by a coordinate mapper. Inputs that map outside the bounds of the input sheet are treated as having zero weight.

Nested Classes

[hide private]

Inherited from param.parameterized.Parameterized: __metaclass__

Instance Methods

[hide private]

__init__(self, **kw)
x.__init__(...) initializes x; see x.__class__.__doc__ for signature

source code

activate(self, input)
Compute an activity matrix for output, based on the specified input_activity.

source code

learn(self)
This function has to be re-implemented by sub-classes, if they wish to support learning.

source code

Inherited from base.projection.Projection: apply_learn_output_fn, get_projection_view, override_plasticity_state, restore_plasticity_state

Inherited from base.simulation.EPConnection: remove, script_repr

Inherited from param.parameterized.Parameterized: __getstate__, __repr__, __setstate__, __str__, debug, defaults, force_new_dynamic_value, get_param_values, get_value_generator, inspect_value, message, print_param_values, set_dynamic_time_fn, state_pop, state_push, verbose, warning

Inherited from param.parameterized.Parameterized (private): _check_params, _instantiate_param, _set_name, _setup_params

Inherited from object: __delattr__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__

Class Methods

[hide private]

Inherited from param.parameterized.Parameterized: params, print_param_defaults

Class Variables

[hide private]

coord_mapper = param.ClassSelector(CoordinateMapperFn, default...
Function to map a destination unit coordinate into the src sheet.

weights_generator = param.ClassSelector(PatternGenerator, defa...
Generate initial weight values for each unit of the destination sheet.

output_fn = param.ClassSelector(OutputFn, default= IdentityOF(...
Function applied to the Projection activity after it is computed.

learning_fn = param.ClassSelector(LearningFn, default= Identit...
Learning function applied to weights.

learning_rate = param.Number(default= 0)

Inherited from base.projection.Projection: activity_group, dest_port, plastic, precedence, src_port, strength

Inherited from base.simulation.EPConnection: delay, dest, private, src

Inherited from param.parameterized.Parameterized: name, print_level

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

init(self, **kw)
(Constructor)

source code

x.__init__(...) initializes x; see x.__class__.__doc__ for signature

Overrides: object.__init__: (inherited documentation)

activate(self, input)

source code

Compute an activity matrix for output, based on the specified input_activity.

Subclasses must override this method to whatever it means to calculate activity in that subclass.

Overrides: base.projection.Projection.activate: (inherited documentation)

learn(self)

source code

This function has to be re-implemented by sub-classes, if they wish to support learning.

Overrides: base.projection.Projection.learn: (inherited documentation)

Class Variable Details

[hide private]

coord_mapper

Function to map a destination unit coordinate into the src sheet.

Value:

param.ClassSelector(CoordinateMapperFn, default= IdentityMF(), doc= 'Function to m
ap a destination unit coordinate into the src sheet.')

weights_generator

Generate initial weight values for each unit of the destination sheet.

Value:

param.ClassSelector(PatternGenerator, default= Constant(), constant= True, doc= ""
"Generate initial weight values for each unit of the destination sheet.""")

output_fn

Function applied to the Projection activity after it is computed.

Value:

param.ClassSelector(OutputFn, default= IdentityOF(), doc= 'Function applied to the
 Projection activity after it is computed.')

learning_fn

Learning function applied to weights.

Value:

param.ClassSelector(LearningFn, default= IdentityLF(), doc= """Learning function a
pplied to weights.""")

Class OneToOneProjection

__init__(self, **kw) (Constructor)

activate(self, input)

learn(self)

coord_mapper

weights_generator

output_fn

learning_fn

init(self, **kw)
(Constructor)