The Hebbian module
The hebbian model panel
In Hebbian module the panel to control the simulation is divided into four sections:
- the Net Interface section
with the buttons CONNECT , DISCONNECT and EXIT
to allow the association between the network and the simulation module;
- the Simulation Scheduler with the buttons RUN ,
STEP , STOP , RND WEIGHT , EVAL ,
VAL TRSET , OPTION and some other
tools to manage the simulations;
- the Training Set section with the
buttons NEW , LOAD and IMAGE to manage
the training set generation and the training set files;
- the forth section will
show output data of the simulations and context dependent messages. The
application guides the use of the panel changing the sensitivity of the panel
tools according to the feasible operations at a given phase of the simulation.
The Net Interface section
- CONNECT
- It establishes the connection between the model panel and the
current net; the net is tested to see if the structure is
compatible with the hebbian model architecture.
- DISCONNECT
- It erase the connection to the net, deallocating from memory the
simulation data.
- EXIT
- It closes the Hebbian simulation panel.
The Simulation Scheduler section
- RUN
- It starts/restarts the simulation on the current net, with
current parameters and options settings. While simulation is
running, the STOP and STEP buttons are
sensitive.
- STEP
- It is used to perform a simulation step by step: when used the
simulation runs for a number of steps indacated by the refresh
parameter.
- STOP
- Allows the user to stop the running simulation; this feature is
useful because the simulation time could be quite large, expecially
with big nets (hundreds of neurons), and the user could think to change the
simulation parameters and restart.
- RND WEIGHT
- This button allows to set random values to the arcs weight: this
is useful when the user would restart a new simulation.
- EVAL
- When the learning phase is terminated the user sets the input neurons
whit some value. The EVAL button evaluates the
output values using the arcs weight learned before.
- VAL TRSET
- Like the previous button, it allows to evaluate a set of values
after the learning phase. In image compression, this button allow
to open the compression/quantization dialog box where it is
possible to set all the parameters needed for generating the
compressed file.
- OPTIONS
- Clicking on this button will open an option panel with some
Motif toggle buttons, which allows to set some simulation flags to
modify both model behaviour and output features.
- Origin : Average, Center
- it changes the position where the weight vectors
start.
- Report File :
- selecting yes an output text file is
written, while the simulation is running. The output
file can be found in directory
<INNEHOME>/NOTES and is named
Hebbreport.txt (a successive output will rewrite
the last one); the output file reports different
statistics on data taken after each iteration of the
learning algorithm.
- Training Set :
- input pattern can be presented to the network
in sequence as they are created or in random order.
- Eta Rule : Costant, Linear, Armonic, Exp
- there are four eta decay rules: with Costant rule,
eta value does not change in the
simulation; with the other rules, eta will decay
according to the selected formula.
- Rule : Oja, Sanger, Hebb
- these are the three rules implemented in the Hebbian
module. The user has to select the rule before
connecting the net to the model.
The Simulation Parameters
- Initial Eta Value
- It is the value used for eta by the first simulation
step. While the simulation run, eta value decaies according to
the Eta Rule .
- Learning Cycles
- It represnts the number of steps performed in the simulation.
- Refresh Sequence
- It is the number of steps between two video refreshes.
The Training Set section
- NEW
- If the net has two (or three) input neurons, it is possible to build a
bidimensional (or three-dimensional) composition of gaussian distributions. When the
button is clicked, a new panel opens where the user can set the Gaussian
distributions in the bidimensional (or three-dimensional) space.
- LOAD
- It loads a sequence of example from a training set file; the input
neurons determines the expected format of the file; if this format
is not satisfied, the load fails.
- IMAGE
- This button is used to specify an image file to use as a
training set. This is useful in image compression.
Back to index