topo.responsefn Package

---

responsefn Package

A family of response functions for CFProjections.

These function objects compute a response matrix when given an input pattern and a set of ConnectionField objects. Response functions come in two varieties: ResponseFunction, and CFPResponseFunction. A ResponseFunction (e.g. DotProduct) computes the response due to one CF. To compute the response due to an entire CFProjection, a ResponseFunction can be plugged in to CFPRF_Plugin. CFPRF_Plugin is one example of a CFPResponseFunction, which is a function that works with the entire Projection at once. Some optimizations and algorithms can only be applied at the full CFPResponseFn level, so there are other CFPResponseFns beyond CFPRF_Plugin.

Any new response functions added to this directory will automatically become available for any model.

class topo.responsefn.DotProduct(**params)

Bases: topo.base.functionfamily.ResponseFn

Return the sum of the element-by-element product of two 2D arrays.

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07afed0ec0>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07afed0e68>

inspect_value = <functools.partial object at 0x2b07afed0f18>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07afed0c58>

set_param = <functools.partial object at 0x2b07b0026050>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

class topo.responsefn.ResponseFn(**params)

Bases: param.parameterized.Parameterized

Abstract base class for response functions that plug into CFPRF_Plugin.

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07afed0d08>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07afed0ec0>

inspect_value = <functools.partial object at 0x2b07afed0db8>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07afed0d60>

set_param = <functools.partial object at 0x2b07b0017050>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

---

optimized Module

Response functions and CFProjection response functions (see projfn.py) written in C to optimize performance.

Requires the weave package; without it unoptimized versions are used.

class topo.responsefn.optimized.CFPRF_DotProduct(**params)

Bases: topo.base.cf.CFPRF_Plugin

Wrapper written to allow transparent non-optimized fallback; equivalent to CFPRF_Plugin(single_cf_fn=DotProduct()).

param ClassSelector single_cf_fn (allow_None=False, constant=False, default=<DotProduct DotProduct01274>, instantiate=True, is_instance=True, pickle_default_value=True, precedence=None, readonly=False)

Accepts a ResponseFn that will be applied to each CF individually.

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07afef7158>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07afef7100>

inspect_value = <functools.partial object at 0x2b07afef71b0>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07afef7208>

set_param = <functools.partial object at 0x2b07afef72b8>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

topo.responsefn.optimized.CFPRF_DotProduct_cyopt

alias of CFPRF_DotProduct

class topo.responsefn.optimized.CFPRF_DotProduct_opt(**params)

Bases: topo.base.cf.CFPResponseFn

Dot-product response function.

Written in C for a manyfold speedup; see CFPRF_DotProduct for an easier-to-read version in Python. The unoptimized Python version is equivalent to this one, but it also works for 1D arrays.

param ClassSelector single_cf_fn (allow_None=False, constant=True, default=<DotProduct DotProduct01512>, instantiate=False, is_instance=True, pickle_default_value=True, precedence=None, readonly=True)

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07b0006208>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07b0006310>

inspect_value = <functools.partial object at 0x2b07b0006368>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07b0006730>

set_param = <functools.partial object at 0x2b07b0006788>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

class topo.responsefn.optimized.CFPRF_EuclideanDistance_opt(**params)

Bases: topo.base.cf.CFPResponseFn

Euclidean-distance response function.

Written in C for a several-hundred-times speedup; see CFPRF_EuclideanDistance for an easier-to-read (but otherwise equivalent) version in Python.

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07b0006158>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07b0006100>

inspect_value = <functools.partial object at 0x2b07b0006208>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07b0006260>

set_param = <functools.partial object at 0x2b07b0006310>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

---

projfn Module

Projection-level response functions.

For CFProjections, these function objects compute a response matrix when given an input pattern and a set of ConnectionField objects.

class topo.responsefn.projfn.CFPRF_EuclideanDistance(**params)

Bases: topo.base.cf.CFPResponseFn

Euclidean-distance–based response function.

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07af2a9998>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07af2a95d0>

inspect_value = <functools.partial object at 0x2b07af2a9aa0>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07af2a99f0>

set_param = <functools.partial object at 0x2b07af2a9158>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

class topo.responsefn.projfn.CFPRF_ActivityBased(**params)

Bases: topo.base.cf.CFPResponseFn

Calculate the activity of each unit nonlinearly based on the input activity.

The activity is calculated from the input activity, the weights, and a strength that is a function of the input activity. This allows connections to have either an excitatory or inhibitory effect, depending on the activity entering the unit in question.

The strength function is a generalized logistic curve (Richards’ curve), a flexible function for specifying a nonlinear growth curve:

y = l + ( u /(1 + b exp(-r (x - 2m)) ^ (1 / b)) )

This function has five parameters:

* l: the lower asymptote, i.e. the value at infinity;
* u: the upper asymptote minus l, i.e. (u + l) is the value at minus infinity;
* m: the time of maximum growth;
* r: the growth rate;
* b: affects near which asymptote maximum growth occurs.

Richards, F.J. 1959 A flexible growth function for empirical use. J. Experimental Botany 10: 290–300, 1959. http://en.wikipedia.org/wiki/Generalised_logistic_curve

param Number b (allow_None=False, bounds=None, constant=False, default=2, inclusive_bounds=(True, True), instantiate=False, pickle_default_value=True, precedence=None, readonly=False, time_dependent=True, time_fn=<Time Time00001>)

Controls position of maximum growth

param ClassSelector single_cf_fn (allow_None=False, constant=False, default=<DotProduct DotProduct01511>, instantiate=True, is_instance=True, pickle_default_value=True, precedence=None, readonly=False)

ResponseFn to apply to each CF individually.

param Number m (allow_None=False, bounds=None, constant=False, default=0.25, inclusive_bounds=(True, True), instantiate=False, pickle_default_value=True, precedence=None, readonly=False, time_dependent=True, time_fn=<Time Time00001>)

Time of maximum growth.

param Number l (allow_None=False, bounds=None, constant=False, default=-1.3, inclusive_bounds=(True, True), instantiate=False, pickle_default_value=True, precedence=None, readonly=False, time_dependent=True, time_fn=<Time Time00001>)

Value at infinity

param Number r (allow_None=False, bounds=None, constant=False, default=-200, inclusive_bounds=(True, True), instantiate=False, pickle_default_value=True, precedence=None, readonly=False, time_dependent=True, time_fn=<Time Time00001>)

Growth rate, controls the gradient

param Number u (allow_None=False, bounds=None, constant=False, default=1.2, inclusive_bounds=(True, True), instantiate=False, pickle_default_value=True, precedence=None, readonly=False, time_dependent=True, time_fn=<Time Time00001>)

(u + l) is the value at minus infinity

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07af2a9838>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07af2a9940>

inspect_value = <functools.partial object at 0x2b07af2a9e68>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07af2a9af8>

set_param = <functools.partial object at 0x2b07af2a97e0>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

class topo.responsefn.projfn.CFPRF_Plugin(**params)

Bases: topo.base.cf.CFPResponseFn

Generic large-scale response function based on a simple single-CF function.

Applies the single_cf_fn to each CF in turn. For the default single_cf_fn of DotProduct(), does a basic dot product of each CF with the corresponding slice of the input array. This function is likely to be slow to run, but it is easy to extend with any arbitrary single-CF response function.

The single_cf_fn must be a function f(X,W) that takes two identically shaped matrices X (the input) and W (the ConnectionField weights) and computes a scalar activation value based on those weights.

param ClassSelector single_cf_fn (allow_None=False, constant=False, default=<DotProduct DotProduct01274>, instantiate=True, is_instance=True, pickle_default_value=True, precedence=None, readonly=False)

Accepts a ResponseFn that will be applied to each CF individually.

debug(msg, *args, **kw)

Print msg merged with args as a debugging statement.

See Python’s logging module for details of message formatting.

defaults()

Return {parameter_name:parameter.default} for all non-constant Parameters.

Note that a Parameter for which instantiate==True has its default instantiated.

force_new_dynamic_value = <functools.partial object at 0x2b07af2a9578>

get_param_values(onlychanged=False)

Return a list of name,value pairs for all Parameters of this object.

If onlychanged is True, will only return values that are not equal to the default value.

get_value_generator = <functools.partial object at 0x2b07af2a9838>

inspect_value = <functools.partial object at 0x2b07af2a99f0>

message(msg, *args, **kw)

Print msg merged with args as a message.

See Python’s logging module for details of message formatting.

classmethod params(parameter_name=None)

Return the Parameters of this class as the dictionary {name: parameter_object}

Includes Parameters from this class and its superclasses.

pprint(imports=None, prefix=' ', unknown_value='<?>', qualify=False, separator='')

(Experimental) Pretty printed representation that may be evaluated with eval. See pprint() function for more details.

classmethod print_param_defaults()

Print the default values of all cls’s Parameters.

print_param_values()

Print the values of all this object’s Parameters.

script_repr(imports=, []prefix=' ')

Variant of __repr__ designed for generating a runnable script.

classmethod set_default(param_name, value)

Set the default value of param_name.

Equivalent to setting param_name on the class.

set_dynamic_time_fn = <functools.partial object at 0x2b07af2a95d0>

set_param = <functools.partial object at 0x2b07af2a91b0>

state_pop()

Restore the most recently saved state.

See state_push() for more details.

state_push()

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.

verbose(msg, *args, **kw)

Print msg merged with args as a verbose message.

See Python’s logging module for details of message formatting.

warning(msg, *args, **kw)

Print msg merged with args as a warning, unless module variable warnings_as_exceptions is True, then raise an Exception containing the arguments.

See Python’s logging module for details of message formatting.

---