What is an artificial neural network? The basic idea of artificial neural networks

Jiu Jiu Candy is so detailed, I wanted to say something, but it seems that I don't need to say anything.

To put it simply, normalizing the way of thinking of people, simulating people's thinking, can enable computers to learn and judge on their own (but so far no cutting-edge results can simulate even the thinking of young children, people are too great!!

Hello, the basic idea of artificial neural networks is to combine the understanding of biological neural networks with mathematical statistical models, and realize them with the help of mathematical statistical tools.

Think of this network as a model of computation, consisting of a large number of nodes (or neurons) that are connected to each other. Each node represents a specific output function, called the activation function. Each connection between two nodes represents a weighted value of the signal that passes through the connection, called a weight, and in this way neural networks simulate human memory.

Artificial neural network is a kind of non-programmed, adaptive, brain-style information processing, the essence of which is to obtain a parallel distributed information processing function through the transformation and dynamic behavior of the network, and imitate the information processing function of the human brain nervous system to different degrees and levels.

The rapid development of artificial intelligence is also due to the maturity of artificial intelligence technology. Artificial intelligence is inseparable from neural networks, and neural networks have also gone through a very rugged road in the development of artificial intelligence, so what is the difference between artificial intelligence and neural networks?

1. The reference is different. Artificial intelligence: It is a new technical science that researches and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; Neural Networks:

It is an algorithmic mathematical model that imitates the behavioral characteristics of animal neural networks and performs distributed parallel information processing.

2. Different methods. Artificial intelligence: an attempt to understand the essence of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence, including robotics, language recognition, image recognition, natural language processing, and expert systems. Neural Networks:

Relying on the complexity of the system, the purpose of processing information is achieved by adjusting the interconnection between a large number of internal nodes.

3. Different purposes. Artificial intelligence: The main goal is to enable machines to do some complex jobs that would normally require human intelligence to complete; Neural Networks:

Initial self-adaptation and self-organization ability. Synaptic weight values are changed during learning or training to suit the requirements of the surrounding environment. The same network can have different functions depending on the learning method and content.

A complete artificial neural network consists of an input layer, one or more hidden layers, and an output layer.

Neural networks, also known as artificial neural networks (ANNs) or simulated neural networks (SNNs), are a subset of machine learning and are at the heart of deep learning algorithms. Its name and structure are inspired by the human brain, mimicking the way biological neuronal signals pass to each other.

An artificial neural network (ANN) consists of a nodal layer consisting of an input layer, one or more hidden layers, and an output layer. Each bridge node is also known as an artificial neuron, and they are connected to another node with associated weights and thresholds. If the output of any single node is above the specified threshold, then that node will be activated and the data will be sent to the next layer of the network.

Otherwise, the data is not passed to the next layer of the network.

Once the input layer has been determined, the weights are assigned. These weights help determine the importance of any given variable, with larger weights contributing more to the output than other inputs. Multiply all inputs by their respective weights and sum.

After that, the output is passed through an activation function that determines the output result.

If that output exceeds a given threshold, then it will "trigger" (or activate) a node to pass the data to the next layer in the network. This causes the output of one node to become the input of the next. This process of passing data from one layer to the next defines the neural network as a feedforward network.