Skip to main content

Table 3 Procedure of the General MFNN algorithm

From: Matrix factorization with neural network for predicting circRNA-RBP interactions

Algorithm 1: The General MFNN Algorithm
Input:Y: the known interaction matrix
Set: Epoch: e, Batch size: b, Learning rate: l
Output:W: model parameters
1: Randomly sample the train set Ytrain  and validation set  Yvali from  Y.
2: Initialize the model parameters  wc _ n  and  wr _ n  with a Gaussian distribution
3: while not model is converged and epoch > e do
 sample a mini batch from  Ytrain  in size b
 set pri  and  qcj  using Eq. 2 and 3 with mini batch
 set  fi, j  using Equation 4 with  pri  and  qcj
 set  L using Equation 5 with  fi, j and  yij
 use Adam optimizer to optimize model parameters
end while
4: using the  Yvali  evaluate the model