Prediction of Punching Capacity of Slab-Column Connections without Transverse Reinforcement Based on a Backpropagation Neural Network

Figure 5

Linear regression between the neural network output and the expected output. (a) Training: R = 0.99663. (b) Validation: R = 0.98419. (c) Test: R = 0.98922. (d) All: R = 0.99342.

(a)

(b)

(c)

(d)