1, hidden Markov model
Hidden Markov Model (HMM) is a dynamic Bayesian network with the simplest structure and a particularly famous directed graph structure. Mainly used in time series data modeling, widely used in speech recognition, natural language processing and other fields.
In word segmentation algorithms, hidden Markov is often used as an algorithm to find new words. Through massive data learning, people's names, place names and network neologisms can be recognized one by one, which has a wide range of application scenarios.
2. Snack food brands
Well, it is a snack brand exclusively for young women in the Internet field, and it is also the first snack dedicated to young girls in the food field in China. Not only pay attention to food, but also pay attention to the growth story of a generation. Xi' an Han Meimei Electronic Commerce Co., Ltd. was established in February 20 15. Its headquarters is in Xi, China, and its main operation team is located in Beijing, China.
basic theory
Hidden Markov model is a kind of Markov chain, and its state cannot be observed directly, but it can be observed through the sequence of observation vectors. Each observation vector represents various states through a certain probability density distribution, and each observation vector is generated by a state sequence corresponding to the probability density distribution.
Therefore, the hidden Markov model is a double stochastic process-a hidden Markov chain with a certain number of states and a set of explicit random functions. Since 1980s, HMM has been applied to speech recognition and achieved great success.
In 1990s, HMM was also introduced into the core technology of computer character recognition and mobile communication "multi-user detection". HMM is also applied in bioinformatics, fault diagnosis and other fields.
Reference to the above content: Baidu Encyclopedia-Hmm