# What is the Perceptron Kernel predictor function?

I am trying to implement a kernalised perceptron, and one thing that I can't understand is what at the end is the predictor function and how do we use it?

I know that the update rule is $$\left (y_i \sum^n_{j=1}\alpha_jy_j \right) < 0$$ And then we update the $$\alpha_i$$.

But what does the $$h(x)$$ is equal to? What I can't understand is that if I am given a new data point $$z$$, what do I do with it? What's the explicit formula for this? I look all over the internet, but it's really unclear for me.