`COMMON /JNINT1/ O(MAXV),A(MAXV),D(MAXV),T(MAXV),DT(MAXV),W(MAXM),`

DW(MAXM),NSELF(MAXM),NTSELF(MAXV),G(MAXM+MAXV),

ODW(MAXM),ODT(MAXV),ETAV(MAXM+MAXV)

`/JNINT1/`contains weight and node vectors for the net. Node vectors are`O`,`A`,`D`,`T`,`DT`,`NTSELF`and`ODT`. Weight vectors are`W`,`DW`,`NSELF`,`G`,`ODW`and`ETAV`. The default dimensions for these vectors are`MAXV`= 2000 and`MAXM`= 150000.`O(I)`current value of node`I`in the network, does not include the input units`A(I)`current value of the summed input to node`I``D(I)`current value of the at node`I``T(I)`current value of the threshold (see eq. ()) at node`I``DT(I)`current value of the update for the threshold at node`I``W(IW)`current value for weight with index`IW``DW(IW)`current value of the update for weight with index`IW``NSELF(IW)`switches for updating weight with index`IW`0 do not update

1 update

for self-organizing map,

`NSELF`is equivalent to the vector`NBHD``NTSELF(I)`switches for updating threshold for node`I`.0 do not update

1 update

`G(IW)`temporary weight and threshold vector used in CG, SCG and QP`ODW(IW)`stores old weight gradient in CG, SCG, QP and Rprop`ODT(I)`stores old threshold gradient in CG, SCG, QP and Rprop`ETAV(IW)`individual learning rates used in Rprop`COMMON /JNINT2/ M(0:10),MV0(11),MM0(11),NG(10),NL,IPOTT,ER1,ER2,SM(10),ICPON`

`/JNINT2/`contains pointers and internal switches for the feed-forward network.`M(I)`number of nodes in layer`I`(`I`=0 input layer)`MV0(I)`offset index for node vectors - tells the index in the node vectors for thelast node in layer (

`I-1`)`MM0(I)`offset index for weight vectors - tells the index in the weight vectors forthe last weight going from layer (

`I-1`)`NG(I)`activation function for layer`I``NL`number of layers except input layer`IPOTT`switch for use of Potts units`IPOTT`= dimension of Potts units`ER1, ER2`internal variables used for calculating`PARJN(7-9)``SM(I)`internal variable used for calculating saturation measures`ICPON`switch for precision chopping1 on

`COMMON /JNINT3/ NXIN,NYIN,NXRF,NYRF,NXHRF,NYHRF NHRF,NRFW,NHPRF`

`/JNINT3/`common block for receptive fields indices.

The geometry of the receptive fields is defined as follows: The input nodes are assumed to be organized in a plane of`NXIN`x-width of input field (if negative periodic boundary)set from

`MSTJN(23)``NYIN`y-height of input-field (if negative periodic boundary)set from

`MSTJN(24)``NXRF`x-width of the receptive field -- set from`MSTJN(25)``NYRF`y-height of receptive field -- set from`MSTJN(26)``NXHRF`number of overlapping receptive field in x-direction`NYHRF`number of overlapping receptive fields in y-direction`NHRF`total number of receptive fields`NRFW`number of weights per receptive field`NHPRF`number of nodes per receptive field -- set from`MSTJN(27)`If

`NHPRF`is negative, weights from equivalent receptive field nodes in thefirst hidden layer to each node in the second hidden layer are shared.

`NXIN*NYIN`nodes (with periodic boundaries if`NXIN`or`NYIN`are negative). Note that the coordinates`(IX,IY)`corresponds to input node number`IN=(IX-1)*NYIN+IY`. Each receptive field node in the first hidden layer scan an area of`NXRF*NYRF`input nodes.`COMMON /JNINT4/ ILINON,NC,G2,NIT,ERRLN(0:3),DERRLN,STEPLN(0:3),`

STEPMN,ERRMN,IEVAL,ISUCC,ICURVE,NSC,GVEC2

`/JNINT4/`common block for CG line search parameters and SCG parameters.`ILINON`switch that tells the current status of the line search.0 off

1 on and trying to bracket the minimum

-1 on and looking for the minimum (knowing that its been bracketed)

`NC`number of steps taken in CG minimization`G2`squared magnitude of the vectors`DW(IW)`and`DT(I)``NIT`number of calls to the line search (along current direction)`ERRLN(I)`stored errors used in line search`I`=0 current error`I`**>**0 previous errors`DERRLN`gradient along search direction at initial point`STEPLN(I)`coordinates, relative to current position, for previous points corresponding to`ERRLN(I)``STEPMN`position, relative to current point, of best minimum so far`ERRMN`minimum error so far`IEVAL`switch for the comparison parameter in SCG training0 do not compute the comparison parameter

1 compute the comparison parameter

`ISUCC`switch that tells if a successful step was made in the SCG algorithmsuccessful step

`ICURVE`switch to tell whether curvature information exists or not -- used in the SCG algorithm.0 curvature information does not exist

1 curvature information exists

`NSC`number of attempted steps in the SCG algorithm`GVEC2`squared magnitude of the vector`G(IW)``COMMON /JNINT5/ D2E(MAXD2E,MAXD2E)`

`/JNINT5/`common block used to store the Hessian matrix.`D2E(IW,IW)`the Hessian matrix`COMMON /JNSIGM/ GPJN(MAXV),GPPJN(MAXV)`

`/JNSIGM/`common block containing first and second derivatives of the activation function . They are computed when the function`GJN`is called.`GPJN(I)`first derivative`GPPJN(I)`second derivative

Fri Feb 24 11:28:59 MET 1995