461.461. Graph Convolutional Network

Graph convolutional networks (GCNs) are a type of neural network designed to handle graph-structured data. They work by performing a series of graph convolutions to update the node representations. In this problem, you will implement a basic GCN using the graph convolutional layer.

**Example:** Suppose we have a graph with three nodes and two edges. We can use the graph convolutional layer to update the node representations based on the neighboring nodes.

**Constraints:** You must use NumPy to implement the graph convolutional layer. You must also use a specific activation function to update the node representations.