Data Anylitics
Description
Vocal Characteristics
Language
EnglishVoice Age
Young Adult (18-35)Accents
North American (General)Transcript
Note: Transcripts are generated using speech recognition software and may contain errors.
introduction. As computers and the Internet become more and more in all aspects of life, the data collected by people has also grown exponentially. In this case, large data big data came into being. Big data is usually very large and complex, making it impossible to store and manage it directly. Using traditional database tools. Big data brings many challenges, such as data collection, organization storage, sharing analysis and visualization. Generalized big data processing covers all of the above areas narrowly defined Big data refers more toe how to use machine learning to analyze big data and analyze useful information from massive data. At the heart of big data analysis is machine learning algorithms. Many times we have enough data, but we don't understand how to use it. At the same time, the actual problems are often complicated and the machine learning algorithm cannot be directly applied. We need to transform the actual problems so that the machine learning algorithm can be applied. Although actual problems manifest themselves in different ways when they were transformed into problems that machine learning can deal with, they generally turn it into the following four types of problems. Regression problems, classifications, problems, recommendation problems sorting problem. Deep learning is a subset of machine learning, while machine learning is a subset of artificial intelligence. A. I. Broadly speaking, any computer program that can perform some kind of intelligent activity is artificial intelligence. It can be a bunch of, if then statements or a complex statistical model. Whenever an artificial intelligence researcher designs a computer program that is good at a certain task, such as playing chess, many people usually say this is not true intelligence because people fully understand the internal principles of their algorithms. So it can be said that true artificial intelligence is something that any computer can't do now. It is often said that machine learning is a subset of artificial intelligence. This means that all machine learning can be counted as artificial intelligence. But not all. Artificial intelligence is machine learning, for example, symbolic logic, rule, engine expert system and knowledge map, evolutionary algorithms and dais. Since statistics can all be called artificial intelligence, but they are not machine learning. Machine learning includes the word learning. Because machine learning algorithms try to optimize a particular metric, they generally try to minimize the error of prediction or to maximize the probability of prediction such an algorithm as three names, an error function, a loss function and an objective function because this algorithm as a target. If someone says they are using a machine learning algorithm and then just asks two questions to get an idea of the value of the algorithm, Deep learning is a subset of machine learning. Deep Artificial Neural Network is a kind of algorithm that continuously refreshes the accuracy rate record on important issues such as image recognition, voice recognition and recommendation system. Depth is a term it refers to the number of layers in a neural network. Shallow neural networks have a so called hidden layer, while deep neural networks have more than one hidden layer multiple hidden layers allowed. Deep neural networks toe learn the characteristics of data in a layered manner because simple features such as two pixels can be layer by layer superimposed to form more complex features such as a straight line