A Neural Network Primer

Introduction to Neural Network This article explains the basic knowledge on the topics of neural networks. People who are not used to the topic of the neural network advise and suppose that the reader has basic algebra knowledge. Please do not hesitate to distribute this paper. However, please distribute the full text without deleting and limit the correction and addition to the space below the bottom line after the last paragraph of the original text. If you want to change or change the original text body, please submit your suggestion to the computer address above me.

In February 2018 I reviewed the developer Week Hackathon and gave a lecture at the Developer Week Conference held in San Fransisco. My presentation is an introduction to the neural network of developers of events in artificial intelligence (AI) orbit. This is a wonderful experience! I am a South African from Johannesburg. After the event, I decided to explore San Francisco, Los Angeles, Las Vegas on vacation. The idea of ​​talking at a meeting of the World Science and Technology Innovation Center and the idea of ​​traveling a country that has never been before has been exciting and scary for various reasons.

Let's begin by discussing the neural network. Neural network is an artificial intelligence method based on the human brain. We know that the human brain consists of billions of interconnected neurons. The neural network trains a large amount of data and each layer of the neuron develops a task to perform input from input to input to input. These types of neural networks are the foundation for many of the greatest advances in AI in the past few years, from new outcomes of accurate medical diagnosis to victories of Google and AlphaGo.

A third-generation neural network, a pointed neural network, aims to fill the gap between neuroscience and machine learning using a biologically realistic neuron model for computation. The spike neural network (SNN) is fundamentally different from the neural network known to the machine learning community. SNN works with spikes. Spikes are not continuous values, but are individual events occurring at some point. The appearance of spikes is determined by differential equations representing various biological processes, the most important of which is the membrane potential of neurons. Essentially, when a neuron reaches a certain potential, it jumps up and the potential of the neuron is reset. The most common model is the Leaky integrated ignition (LIF) model. In addition, SNN is usually loosely coupled and uses a special network topology.