Baidu Encyclopedia version

Artificial Neural Network (ANN) is a research hotspot in the field of artificial intelligence since the 20 century 80 era. It abstracts the human brain neuron network from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods.

In engineering and academia, it is often referred to directly as a neural network or a neural network. A neural network is an operational model consisting of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function called an activation function. The connection between every two nodes represents a weighting value for passing the connection signal, called weight, which is equivalent to the memory of the artificial neural network. The output of the network varies depending on the connection method of the network, the weight value and the excitation function. The network itself is usually an approximation of an algorithm or function in nature, or it may be an expression of a logic strategy.

In the past ten years, the research work of artificial neural networks has been deepened, and great progress has been made. It has successfully solved many problems in the fields of pattern recognition, intelligent robots, automatic control, predictive estimation, biology, medicine, and economy. The practical problems that modern computers are difficult to solve show good intelligence.

see details

 

Wikipedia version

An artificial neural network (ANN) or a connected system is a computational system that is ambiguously inspired by the biological neural network that makes up the animal's brain. The neural network itself is not an algorithm, but a framework for many different machine learning algorithms that work together and handle complex data inputs. Such systems perform tasks by considering the example "learning", usually without any task-specific rules. For example, in image recognition, they may learn to identify images containing cats as "cats" or "no cats" by analyzing manual sample images and use the results to identify cats in other images. They do this without any prior knowledge about the cat, for example, they have fur, tail, beard and cat-like faces. Instead, they automatically generate recognition features from the learning materials they process.

ANNs are based on a collection of connected units or nodes called artificial neurons that loosely mimic neurons in the biological brain. Each connection, such as a synapse in a biological brain, can pass signals from one artificial neuron to another. Artificial neurons that receive the signal can process it and then signal other artificial neurons connected to it.

In a common ANN implementation, the signals at the junctions between artificial neurons are real numbers, and the output of each artificial neuron is calculated by some non-linear function of the sum of its inputs. The connection between artificial neurons is called the "edge." Artificial neurons and edges usually have weight that is adjusted as learning progresses. The weight increases or decreases the strength of the signal at the junction. Artificial neurons may have a threshold such that the signal is only sent when the aggregated signal exceeds the threshold. Typically, artificial neurons are aggregated into layers. Different layers can perform different types of conversions on their inputs. The signal may propagate from the first layer (input layer) to the last layer (output layer) after traversing the layers multiple times.

The original goal of the artificial neural network approach was to solve the problem in the same way as the human brain. However, over time, attention shifts to performing specific tasks, leading to deviations from biology. Artificial neural networks have been used for a variety of tasks, including computer vision, speech recognition, machine translation, social network filtering, game boards and video games, and medical diagnostics.

see details

 

Dry goods | Simple understanding of several basic problems of neural networks