Package topo :: Package transferfn :: Module basic :: Class HomeostaticMaxEnt

Class HomeostaticMaxEnt

Implementation of homeostatic intrinsic plasticity from Jochen Triesch, ICANN 2005, LNCS 3696 pp.65-70.

A sigmoid activation function is adapted automatically to achieve desired average firing rate and approximately exponential distribution of firing rates (for the maximum possible entropy).

Note that this TransferFn has state, so the history of calls to it will affect future behavior. The plastic parameter can be used to disable changes to the state.

Also calculates average activity as useful debugging information, for use with ValueTrackingOutoutFn Average activity is calculated as an exponential moving average with a smoothing factor (smoothing). For more information see: NIST/SEMATECH e-Handbook of Statistical Methods, Single Exponential Smoothing http://www.itl.nist.gov/div898/handbook/pmc/section4/pmc431.htm

Nested Classes

[hide private]

Inherited from param.parameterized.Parameterized: __metaclass__

Instance Methods

[hide private]

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

source code

__call__(self, x)

source code

state_push(self)
Save this instance's state.

source code

state_pop(self)
Restore the most recently saved state.

source code

Inherited from TransferFnWithState: override_plasticity_state, restore_plasticity_state

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, script_repr, set_default, set_dynamic_time_fn, set_param, verbose, warning

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

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

Class Methods

[hide private]

Inherited from param.parameterized.Parameterized: params, print_param_defaults

Class Variables

[hide private]

eta = param.Number(default= 0.0002, doc= "Learning rate for ho...
Learning rate for homeostatic plasticity.

mu = param.Number(default= 0.01, doc= "Target average firing r...
Target average firing rate.

smoothing = param.Number(default= 0.9997, doc= ...
Weighting of previous activity vs.

a_init = param.Parameter(default= None, doc= "Multiplicative p...
Multiplicative parameter controlling the exponential.

b_init = param.Parameter(default= None, doc= "Additive paramet...
Additive parameter controlling the exponential.

step = param.Number(default= 1, doc= """ How often to update t...
How often to update the a and b parameters.

name = <param.parameterized.String object at 0xb5897ac>
String identifier for this object.

Inherited from TransferFnWithRandomState: random_generator

Inherited from TransferFnWithState: plastic

Inherited from base.functionfamily.TransferFn: norm_value

Inherited from param.parameterized.Parameterized: print_level

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

init(self, **params)
(Constructor)

source code

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

Overrides: object.__init__: (inherited documentation)

call(self, x)
(Call operator)

source code

Overrides: base.functionfamily.TransferFn.__call__

state_push(self)

source code

Save this instance's state.

For Parameterized instances, this includes the state of dynamically generated values.

Subclasses that maintain short-term state should additionally save and restore that state using state_push() and state_pop().

Generally, this method is used by operations that need to test something without permanently altering the objects' state.

Overrides: param.parameterized.Parameterized.state_push: (inherited documentation)

state_pop(self)

source code

Restore the most recently saved state.

See state_push() for more details.

Overrides: param.parameterized.Parameterized.state_pop: (inherited documentation)

Class Variable Details

[hide private]

eta

Learning rate for homeostatic plasticity.

Value:

param.Number(default= 0.0002, doc= "Learning rate for homeostatic plasticity.")

mu

Target average firing rate.

Value:

param.Number(default= 0.01, doc= "Target average firing rate.")

smoothing

Weighting of previous activity vs. current activity when calculating the average.

Value:

param.Number(default= 0.9997, doc= """
        Weighting of previous activity vs. current activity when calculating the a
verage.""")

a_init

Multiplicative parameter controlling the exponential.

Value:

param.Parameter(default= None, doc= "Multiplicative parameter controlling the expo
nential.")

b_init

Additive parameter controlling the exponential.

Value:

param.Parameter(default= None, doc= "Additive parameter controlling the exponentia
l.")

step

How often to update the a and b parameters. For instance, step=1 means to update it every time this OF is called; step=2 means to update it every other time.

Value:

param.Number(default= 1, doc= """ How often to update the a and b parameters.  For
 instance, step=1 means to update it every time this OF is
        called; step=2 means to update it every other time.""")

Class HomeostaticMaxEnt

__init__(self, **params) (Constructor)

__call__(self, x) (Call operator)

state_push(self)

state_pop(self)

eta

mu

smoothing

a_init

b_init

step

init(self, **params)
(Constructor)

call(self, x)
(Call operator)