Question

4. Consider the multi-layer perceptron whose architecture is defined by three matrixes of synaptic weights with the following dimensions: W₁ E R6 x 8, W₂ E R4x7, W3 ER3 X5

a) How many features are applied to the MLP? (1 Point)
b) What is the number of neurons in each layer n₁, n₂, n3? (1 point)
c) What is the number of classes? (1 Point)

Answer 1

The number of features applied to the MLP is 8. The number of neurons in each layer are 6, 4, and 3. The number of classes cannot be determined from the given information.

Step-by-step explanation:

a) The number of features applied to the MLP can be determined by examining the dimensions of the first weight matrix, W₁. In this case, W₁ has dimensions 6x8, indicating that there are 8 features being passed into the MLP.

b) The number of neurons in each layer can be determined by examining the dimensions of the weight matrices. From the provided information, we have n₁=6 (since the first weight matrix has 6 rows), n₂=4 (since the second weight matrix has 4 rows), and n₃=3 (since the third weight matrix has 3 rows).

c) The number of classes cannot be determined from the given information. The number of classes would depend on the specific problem the MLP is being used to solve.