Skip to main content
. Author manuscript; available in PMC: 2021 Apr 29.
Published in final edited form as: Phys Chem Chem Phys. 2020 Apr 29;22(16):8373–8390. doi: 10.1039/d0cp00305k

Figure 2:

Figure 2:

An illustration of a typical MT-DNN training four tasks (datasets) simultaneously. Four hidden layers are included in this network, ki (i = 1, 2, 3, 4) represents the number of neurons in the ith hidden layer and Ni,j is the jth neuron in the ith hidden layer. Here O1 to O4 represent four predictor outputs for four tasks.