Page 173 - Data Science Algorithms in a Week
P. 173
The Estimation of Cutting Forces in the Turning of Inconel 718 Assisted … 157
effectively in the evolution to find a near-optimal set of connection weights globally,
because they does not require gradient and differentiable information.
The supervised learning process of the ANN based on a bio-inspired algorithm uses
the weights of synapses linking the input layer nodes to hidden layer nodes wjk and
(1)
(1)
hidden layer nodes to output layer nodes wik , respectively. Furthermore, the learning
(1)
(2)
variables are also the bias in nodes of hidden layers bk and output layers bk . The
proposed optimization problem formulation is usually based on the minimization of an
error function, by iteratively adjusting connection weights. A schematic representation of
the learning of ANN using bio-inspired algorithms is given in Figure 3.
Figure 3. Flowchart of bio-inspired ANN.
