| i | an input unit |
| h | a hidden unit |
| o | an output unit |
| | |
| xp | the p-th input pattern vector |
| xpj | the j-th element of the p-th input pattern vector |
| sp | the input to a set of neurons when input pattern vector p is clamped (i.e. presented to the network); often: then input of the network by clamping input pattern vector p |
| dp | the desired output of the network when input pattern vector p was input to the network |
| dpj | the j-th element of the desired output of the network when input pattern vector p was input to the network |
| yp | the activation values of the network when input pattern vector p was input to the network |
| ypj | the activation values of element j of the network when input pattern vector p was input to the network |
| W | the matrix of connection weights |
| wj | the weights of the connections which feed into unit j |
| wjk | the weight of the connection from unit j to unit k |
| Fj | the activation function associated with unit j |
| ηjk | the learning rate associated with weight wjk |
| θ | the biases to the units |
| θj | the bias input to unit j |
| Uj | the treshold of unit j in Fj |
| Ep | the error in the output of the network when input pattern vector p is input |
| εp | the energy of the network |
| α | momentum term to reduce the likelihood of the weight changes oscillating
-> ΔWij(n + 1) = η(δjoi) + αΔWij(n) |
