ML Katas

Build and run a minimal Multi-Layer Perceptron (MLP) using torch.nn.

Problem

Construct a 2-layer MLP with ReLU activation for input of size 10 and output of size 2.

• Input: Tensor of shape (batch_size, 10).
• Output: Tensor of shape (batch_size, 2).

Example

import torch.nn as nn

class MLP(nn.Module):
    def __init__(self):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(10, 32),
            nn.ReLU(),
            nn.Linear(32, 2)
        )
    def forward(self, x):
        return self.layers(x)

x = torch.randn(4, 10)
model = MLP()
print(model(x).shape)  # Expected: torch.Size([4, 2])

Solution Sketch

Use nn.Sequential to stack layers. Forward pass applies linear → ReLU → linear. This is a basic building block for neural nets.