Consider a fully connected forward multi-layer perceptron. It has 30 neurons in the i/p layer foll. by two hidden layers and an o/p layer. The first hidden layer has 4 neurons and the second 3 neurons. The o/p layer has only 1 neuron. Assume that no biased parameter parameter in the mul ______.

The correct answer is 135.

To find the total number of connection weights in a fully connected multi-layer perceptron (MLP) without bias parameters, we calculate the number of weights between each successive pair of layers and then sum them up.

Let's define the number of neurons in each layer:
- Input layer: 30 neurons
- First hidden layer: 4 neurons
- Second hidden layer: 3 neurons
- Output layer: 1 neuron

In a fully connected network, the number of weights between two adjacent layers is the product of the number of neurons in those two layers.

1. Weights between the Input layer and the First hidden layer:
Since every neuron in the input layer connects to every neuron in the first hidden layer, the number of weights is:

$30\times 4=120$

2. Weights between the First hidden layer and the Second hidden layer:
The number of weights is:

$4\times 3=12$

3. Weights between the Second hidden layer and the Output layer:
The number of weights is:

$3\times 1=3$

Now, we find the total number of weights by adding the weights from all the connections together:

$\text{Total Weights}=120+12+3=135$

Thus, the total number of weight parameters in the multi-layer perceptron (with no bias parameters) is 135.