Deep Learning (Python) Study Notes 2

Chapter 2 Perceptron

2.1 What is a perceptron?

The perceptron receives multiple input signals and outputs a signal.

The signal from the perceptron will form a stream, transporting information forward.

The signal of the perceptron only has two values: "flow/no flow" (1/0).

In this study note, 0 corresponds to "not transmitting a signal" and 1 corresponds to "transmitting a signal".

In the figure x_{1}, x_{2}is the input signal, yis the output signal, w_{1}and w_{2}is the weight. The ones in the graph \bigcircare called "neurons" or "nodes".

When the input signal is sent to the neuron, it will be multiplied by a fixed weight ( w_{1}x_{1}, w_{2}x_{2}) respectively. The neuron will calculate the sum of the transmitted signals, and only when the sum exceeds a certain limit, it will output 1. This is called "the neuron is activated".

This limit value is called the threshold value here and \Thetais represented by a symbol.

Express the above content using mathematical formulas, as follows:

The larger the weight, the higher the importance of the signal corresponding to that weight.

The weight is equivalent to the resistance in current. Resistance is a parameter that determines how difficult it is for electric current to flow.

The lower the resistance, the greater the current that passes through it. The greater the weight of the perceptron, the greater the signal that passes through.

2.2 Simple logic circuit

2.2.1 AND gate

 AND Gate: A gate circuit with two inputs and one output.

Guess you like

Origin blog.csdn.net/m0_62110645/article/details/132782371