Apply Xavier Uniform Initialization

Problem Statement

Apply Xavier (Glorot) uniform initialization to a linear layer and verify its properties.

Background

Xavier initialization sets weights from a uniform distribution U(-a, a) where a = gain * sqrt(6 / (fan_in + fan_out)). It's designed for layers with Sigmoid/Tanh activations.

Your Task

The starter code creates an nn.Linear(6, 4) layer. Apply Xavier uniform initialization to the layer's weights.

The rest (computing statistics) is pre-filled.

Output Format

Returns a dictionary with "weight_shape", "weight_mean", "weight_std", "weight_min", and "weight_max".

The function xavier_uniform_test() starts by seeding the random number generator with torch.manual_seed(42) to ensure reproducibility.
It then creates a linear layer nn.Linear(6, 4), which has a weight matrix of shape $(4, 6)$ , where $4$ is the number of outputs (fan_out) and $6$ is the number of inputs (fan_in).
The nn.init.xavier_uniform_ function is applied to the linear layer with default gain, which initializes the weights from a uniform distribution $U(-a, a)$ where $a = \sqrt{\frac{6}{6 + 4}} = \sqrt{\frac{6}{10}} = \sqrt{\frac{3}{5}}$ .
The weights are then analyzed to calculate the mean, standard deviation, minimum, and maximum values, which are rounded to 4 decimals to produce the output dictionary.

Problem Statement

Apply Xavier (Glorot) uniform initialization to a linear layer and verify its properties.

Background

Xavier initialization sets weights from a uniform distribution U(-a, a) where a = gain * sqrt(6 / (fan_in + fan_out)). It's designed for layers with Sigmoid/Tanh activations.

Your Task

The starter code creates an nn.Linear(6, 4) layer. Apply Xavier uniform initialization to the layer's weights.

The rest (computing statistics) is pre-filled.

Output Format

Returns a dictionary with "weight_shape", "weight_mean", "weight_std", "weight_min", and "weight_max".

The function xavier_uniform_test() starts by seeding the random number generator with torch.manual_seed(42) to ensure reproducibility.
It then creates a linear layer nn.Linear(6, 4), which has a weight matrix of shape $(4, 6)$ , where $4$ is the number of outputs (fan_out) and $6$ is the number of inputs (fan_in).
The nn.init.xavier_uniform_ function is applied to the linear layer with default gain, which initializes the weights from a uniform distribution $U(-a, a)$ where $a = \sqrt{\frac{6}{6 + 4}} = \sqrt{\frac{6}{10}} = \sqrt{\frac{3}{5}}$ .
The weights are then analyzed to calculate the mean, standard deviation, minimum, and maximum values, which are rounded to 4 decimals to produce the output dictionary.

Problem Statement

Background

Your Task

Output Format

Example:

Constraints:

Test Results

Apply Xavier Uniform Initialization

Problem Statement

Background

Your Task

Output Format

Example:

Constraints:

Test Results