Hello,
I have a question regarding tabular model.
- What are the parameters updated every batch?
- Are the random initializations of the embeddings and the weights and biases (also random) of the linear layers updated?
- Is the computation in forward method, matrix multiply between the weights of the layers and the imbedding matrices?
- If no for 3, can you please explain the computation happening at method forward and the parametrs updated following that.
Thank you!