Neural Networks as a Solution to Big Data in Law Enforcement

INTRODUCTION "The theory is a serious mistake until all the evidence is obtained, so that the judgment becomes biased." This sentence is a fictitious master, Sir Arthur Conan Doyle's novel, Sherlock Holmes It is from. hero. Before attempting to resolve the crime, Sherlock Holmes knew the value of collecting data and thoroughly analyzing the data, and this induction was still a sign of an excellent criminal investigator. Today, databases and recording rooms are filled with information on various crimes, and when viewed from the whole it often leads to the arrest of perpetrators.

The reason for collecting a large amount of data is to support a deep neural network of cars. This is short background. Deep Neural Network became popular in 2012 after deep neural network acquired ImageNet challenge. ImageNet challenge is a computer vision competition focused on image classification. In 2015, Deep Neural Network slightly exceeded the benchmark of ImageNet Challenge for the first time. (Interestingly, the human benchmark is Andrej Karpathy, an artificial intelligence researcher, now being Director of Tesla's ASIC.) ImageNet Challenge has tested only a small fraction of human vision. Nonetheless, the fact that computers can surpass humans with certain visual tasks is even more exciting for those who want to do something better than a human being. Like driving

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 of many of the greatest advances in AI in the past few years, from new outcomes in accurate medical diagnosis to victories in Google and AlphaGo.

Deep learning is based on a neural network. This is a machine learning technique (roughly) inspired by our brains. In this case, Deep = Big - Very big - Neural network. Training of large-scale neural networks is more complicated than conventional machine learning algorithms. However, since neural networks can be generalized to arbitrary linear functions, they can be well scaled as data increases.

Neural networks and deep learning are important topics in the computer science and technology industry and they currently provide the best solution to many problems in image recognition, speech recognition and natural language processing. A number of papers have recently been announced, including artificial intelligence that can do daily amazing things using paint, construction of 3D model, creation of user interface (pix 2 code), creation of images of given sentences, neural network it was done. I am writing a series of articles on neural networks and deep learning I will guide you through the basic concept of an artificial neural network (ANN), I show you an example from a simple network to an analog AND gate. Image recognition task using convolution neural network (CNN), recurrent neural network (RNN)