WinnerTakeAllStdOptim Class Reference

Optimized version of the standard winner-take-all. More...

#include <Neuro/WinnerTakeAllStdOptim.H>

Inheritance diagram for WinnerTakeAllStdOptim:

[legend]

Collaboration diagram for WinnerTakeAllStdOptim:

[legend]

List of all members.

Classes
struct	EvolveJob
Public Member Functions
	WinnerTakeAllStdOptim (OptionManager &mgr, const std::string &descrName="Optimized Winner-Take-All Std", const std::string &tagName="WinnerTakeAllStdOptim")
	Ininitialized constructor.
virtual	~WinnerTakeAllStdOptim ()
	Destructor.
virtual void	reset1 ()
	Reset to initial state just after construction.
Protected Member Functions
virtual void	input (const Image< float > &in)
	Set new input currents for all neurons.
virtual Image< float >	getV () const
	Return all our membrane potential voltages as an Image<float>
virtual void	integrate (const SimTime &t, Point2D< int > &winner)
	Integrate inputs until time t (in s) and update membrane potentials.
virtual void	saccadicSuppression (const bool on)
	Turn saccadic suppression on/off.
virtual void	blinkSuppression (const bool on)
	Turn blink suppression on/off.

---

Detailed Description

Optimized version of the standard winner-take-all.

This is an optimized version of WinnerTakeAllStd which should give the same results, but with better CPU efficiency.

Definition at line 48 of file WinnerTakeAllStdOptim.H.

---

Constructor & Destructor Documentation

WinnerTakeAllStdOptim::WinnerTakeAllStdOptim	(	OptionManager &	mgr,
		const std::string &	descrName = "Optimized Winner-Take-All Std",
		const std::string &	tagName = "WinnerTakeAllStdOptim"
	)

Ininitialized constructor.

The WTA will be resized and initialized the first time input() is called

Definition at line 116 of file WinnerTakeAllStdOptim.C.

WinnerTakeAllStdOptim::~WinnerTakeAllStdOptim

(

)

[virtual]

Destructor.

Definition at line 145 of file WinnerTakeAllStdOptim.C.

---

Member Function Documentation

void WinnerTakeAllStdOptim::blinkSuppression

(

const bool

on

)

[protected, virtual]

Turn blink suppression on/off.

Implements WinnerTakeAllAdapter.

Definition at line 304 of file WinnerTakeAllStdOptim.C.

References OModelParam< T >::getVal(), and WinnerTakeAllAdapter::itsUseBlinkSuppression.

Image< float > WinnerTakeAllStdOptim::getV

(

)

const [protected, virtual]

Return all our membrane potential voltages as an Image<float>

Implements WinnerTakeAllAdapter.

Definition at line 278 of file WinnerTakeAllStdOptim.C.

void WinnerTakeAllStdOptim::input

(

const Image< float > &

in

)

[protected, virtual]

Set new input currents for all neurons.

This will initialize and resize the network if the network is currently uninitialized (e.g., just after construction or reset()).

Implements WinnerTakeAllAdapter.

Definition at line 162 of file WinnerTakeAllStdOptim.C.

References Image< T >::clear(), Image< T >::getDims(), Image< T >::initialized(), NO_INIT, and Image< T >::resize().

void WinnerTakeAllStdOptim::integrate	(	const SimTime &	t,
		Point2D< int > &	winner
	)			[protected, virtual]

Integrate inputs until time t (in s) and update membrane potentials.

Implements WinnerTakeAllAdapter.

Definition at line 180 of file WinnerTakeAllStdOptim.C.

References ASSERT, Image< T >::begin(), Image< T >::beginw(), SimTime::computeDeltaT(), JobServer::enqueueJob(), JobServer::getParallelismHint(), Image< T >::getSize(), Image< T >::getWidth(), Point2D< T >::i, rutz::make_shared(), SimTime::secs(), ModelComponent::start(), and SimTime::ZERO().

void WinnerTakeAllStdOptim::reset1

(

)

[virtual]

Reset to initial state just after construction.

Reimplemented from WinnerTakeAllAdapter.

Definition at line 151 of file WinnerTakeAllStdOptim.C.

References Image< T >::freeMem(), and SimTime::ZERO().

void WinnerTakeAllStdOptim::saccadicSuppression

(

const bool

on

)

[protected, virtual]

Turn saccadic suppression on/off.

Implements WinnerTakeAllAdapter.

Definition at line 295 of file WinnerTakeAllStdOptim.C.

References OModelParam< T >::getVal(), and WinnerTakeAllAdapter::itsUseSaccadicSuppression.

---

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

• src/Neuro/WinnerTakeAllStdOptim.H
• src/Neuro/WinnerTakeAllStdOptim.C