Table 3 Description of SMNN architectures.
From: Novel AI driven approach to classify infant motor functions
SMNN | Hidden layer | Neuron type | Drop out | Hidden layer | Neuron type | Drop out | Hidden layer | Neuron type | Output layer | Neuron type |
|---|---|---|---|---|---|---|---|---|---|---|
1 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 1 | Sigmoid | ||||||
2 | \(N_{stack} \times 50 \rightarrow 100\) | ReLU | 1 | Sigmoid | ||||||
3 | \(N_{stack} \times 50 \rightarrow 200\) | ReLU | 1 | Sigmoid | ||||||
4 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 20% | 50 | PReLU | 1 | Sigmoid | |||
5 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 20% | 100 | PReLU | 1 | Sigmoid | |||
6 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 20% | 200 | PReLU | 1 | Sigmoid | |||
7 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 20% | 50 | PReLU | 20% | 50 | PReLU | 1 | Sigmoid |
8 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 20% | 100 | PReLU | 20% | 100 | PReLU | 1 | Sigmoid |
9 | \(N_{stack} \times 50 \rightarrow 50\) | ReLU | 20% | 200 | PReLU | 20% | 200 | PReLU | 1 | Sigmoid |
