Predicting Slurry Pressure Balance with a Long Short-Term Memory Recurrent Neural Network in Difficult Ground Condition

Figure 2

Typical architecture of deep feedforward network with two hidden layers; and are the inputs and outputs of DFN; is the weight of the connection from the k^th neuron in the (l−1)^th layer to the j^th neuron in the l^th layer; f is the activation function.