Question:
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_________.
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_________.
Show Hint
To calculate the parameters in a neural network layer, use the formula:
\( (\text{neurons_in_previous_layer} \times \text{neurons_in_current_layer}) + \text{neurons_in_current_layer} \).
The first part of the expression is for the weights, and the second part is for the biases.
If the question says "no bias", simply ignore the second part of the formula.
\( (\text{neurons_in_previous_layer} \times \text{neurons_in_current_layer}) + \text{neurons_in_current_layer} \).
The first part of the expression is for the weights, and the second part is for the biases.
If the question says "no bias", simply ignore the second part of the formula.
Updated On: Feb 23, 2026
Hide Solution
Verified By Collegedunia
Correct Answer: 135
Solution and Explanation
Step 1: Understanding the Question:
The question asks for the total number of parameters in a multi-layer perceptron (MLP) with a specific architecture. The parameters in this case are only the weights, as the question states to assume no bias parameters.
Step 2: Network Architecture:
- Input Layer: 30 neurons - Hidden Layer 1: 4 neurons - Hidden Layer 2: 3 neurons - Output Layer: 1 neuron The network is fully connected, meaning every neuron in a layer is connected to every neuron in the next layer.
Step 3: Calculating Weights Between Layers:
The number of weight parameters between two fully connected layers is the product of the number of neurons in those two layers.
- Weights between Input and Hidden Layer 1: The input layer has 30 neurons and Hidden Layer 1 has 4 neurons. \[ \text{Number of weights} = 30 \times 4 = 120 \] - Weights between Hidden Layer 1 and Hidden Layer 2: Hidden Layer 1 has 4 neurons and Hidden Layer 2 has 3 neurons. \[ \text{Number of weights} = 4 \times 3 = 12 \] - Weights between Hidden Layer 2 and Output Layer: Hidden Layer 2 has 3 neurons and the Output Layer has 1 neuron. \[ \text{Number of weights} = 3 \times 1 = 3 \] Step 4: Calculating Total Parameters:
The total number of parameters is the sum of the weights from all connections. \[ \text{Total Parameters} = 120 + 12 + 3 = 135 \] Step 5: Final Answer:
The total number of parameters (weights) in the network is 135.
The question asks for the total number of parameters in a multi-layer perceptron (MLP) with a specific architecture. The parameters in this case are only the weights, as the question states to assume no bias parameters.
Step 2: Network Architecture:
- Input Layer: 30 neurons - Hidden Layer 1: 4 neurons - Hidden Layer 2: 3 neurons - Output Layer: 1 neuron The network is fully connected, meaning every neuron in a layer is connected to every neuron in the next layer.
Step 3: Calculating Weights Between Layers:
The number of weight parameters between two fully connected layers is the product of the number of neurons in those two layers.
- Weights between Input and Hidden Layer 1: The input layer has 30 neurons and Hidden Layer 1 has 4 neurons. \[ \text{Number of weights} = 30 \times 4 = 120 \] - Weights between Hidden Layer 1 and Hidden Layer 2: Hidden Layer 1 has 4 neurons and Hidden Layer 2 has 3 neurons. \[ \text{Number of weights} = 4 \times 3 = 12 \] - Weights between Hidden Layer 2 and Output Layer: Hidden Layer 2 has 3 neurons and the Output Layer has 1 neuron. \[ \text{Number of weights} = 3 \times 1 = 3 \] Step 4: Calculating Total Parameters:
The total number of parameters is the sum of the weights from all connections. \[ \text{Total Parameters} = 120 + 12 + 3 = 135 \] Step 5: Final Answer:
The total number of parameters (weights) in the network is 135.
Was this answer helpful?
0
0
Top Questions on Machine Learning
- Consider the supervised learning task. The objective function being minimized is \( f(w) = w \cdot x \), where \( w \in \mathbb{R} \) is the parameter. Stochastic Gradient Descent with learning rate of 0.10. Let \( w = 10.00 \) be the \( i^{\text{th}} \) iteration (\( w_i \)). The value of \( w \) at the end of iteration \( (i+1) \) is if \( x = 10 \) ________. Round off 2 decimal.
- GATE DA - 2026
- Data Science and Artificial Intelligence
- Machine Learning
- Consider the Ridge LRR is being used to learn prediction function \( y_{\text{pred}} = w^T x \) where \( w, x \in \mathbb{R}^2 \) & mean absolute error (MAE) is used to measure the prediction error. A weight of 0.20 is associated with the regularizer. At an intermediate step of training process assume that the parameter \( w = [-3.00, 4.00]^T \). In the next step for the I/P \( x = [1.00, 2.00]^T \), the predicted value of \( y \) is noted. Let the relation b/w \( x = [x_1, x_2]^T \) & the true value of \( y \) be \( y_{\text{true}} = x_1 + x_2 \). The value of the overall regularized loss for instance is __________ (upto 2 decimal).
- GATE DA - 2026
- Data Science and Artificial Intelligence
- Machine Learning
- Consider that 20 stories of author X and 10 stories of author Y were kept together without mentioning the names of the authors. A classifier was then asked to predict the author (X or Y) of each of the stories. Later out of X's stories 6 were classified as that of Y. On the other hand, out of Y's stories 2 were classified as that of X. Considering X and Y as two classes, then which of the following is/are true?
- GATE DA - 2026
- Data Science and Artificial Intelligence
- Machine Learning
- Which one of the following is true for Ridge Regression (RR)
- GATE DA - 2026
- Data Science and Artificial Intelligence
- Machine Learning
- Consider that you are training a classifier for a 10-class classification problem. Each I/P is represented as a 512 dimensional vector. There are 1000 samples out of which first 100 will be used for testing. Let Leave-one-out-Cross-Validation (LOOCV) be used for selection of the classifier model before testing. Which of the following option is the correct option for no. of validation split that will be generated?
- GATE DA - 2026
- Data Science and Artificial Intelligence
- Machine Learning
View More Questions
Questions Asked in GATE DA exam
- Rishi and Swathi are students of Class 5. Pavan and Tanvi are students of Class 4. Rishi and Pavan are boys. Swathi and Tanvi are girls. These four students played a total of three games of chess. The games were played one after another. A player who lost a game did not participate in any more games. It was observed that:
1. The first game was the only game where two students of the same class played against each other.
2. The students of Class 5 won more games than the students of Class 4.
3. The boys won 2 games and the girl won 1 game.
The student who did not lose any game is:- GATE DA - 2026
- Logical Reasoning
Consider two distinct positive numbers \( m, n \) with \( m > n \). Let \[ x = n^{\log_n m}, \quad y = m^{\log_m n}. \] The relation between \( x \) and \( y \) is -
- GATE DA - 2026
- Logarithms
- The value of \[ \sum_{j=0}^{\infty} \sum_{i=1}^{\infty} 2^{-j} 3^{-i} \] is ________.
- GATE DA - 2026
- Sequences and Series
- S$_1$ = \{x = (x$_1$, x$_2$, x$_3$)$^T$ $\in$ R$^3$ $|$ x$^T$x $\le$ 16\}. Let S$_2$ be subspace of R$^3$ with dimension 2 then Area of S$_1$ $\cap$ S$_2$ ?
- GATE DA - 2026
- Linear Algebra
Let \( M = \left(I_n - \frac{1}{n} 11^T \right) \) be a matrix where \( 1 = (1,1,\dots,1)^T \in \mathbb{R}^n \) and \( I_n \) is the identity matrix of order \( n \). The value of \[ \max_{x \in S} x^T M x \] where \[ S = \{ x \in \mathbb{R}^n \mid x^T x = 1 \} \] is ________.
- GATE DA - 2026
- Linear Algebra
View More Questions