concept input vector in category python

This is an excerpt from Manning's book Math for Programmers: 3D graphics, machine learning, and simulations with Python MEAP V11. Login to get full access to this book.

Table 2.1: Some Python classes representing geometric figures, usable with the draw function.

Class	Constructor example	Description
Polygon	Polygon(*vectors)	Draws a polygon whose vertices (corners) are represented by a list of vectors.
Points	Points(*vectors)	Represents a list of points (dots) to draw, one at each of the input vectors.
Arrow	Arrow(tip) Arrow(tip, tail)	Draws an arrow from the origin to the tip vector or from the tail vector to the head vector if a tail is specified.
Segment	Segment(start,end)	Draws a line segment from the start to the vector end.

To evaluate a neural network as a mathematical function, there are three basic steps, which I describe in terms of the activation values. I’ll walk through them conceptually and then I’ll show you the formulas. Remember, a neural network is just a function that takes an input vector and produces an output vector. The steps in between are just a recipe for getting to the output from the given input. Here’s the first step in the pipeline.

Figure 16.8: Setting the input layer activations to the entries of the input vector (left)