Models for sequence data / produced by Springer Nature.

Format:

Video

Contributor:

Huang, Bert, speaker.

Springer Nature (Firm), film distributor, production company.

Series:

Academic Video Online

Language:

English

Subjects (All):

Hidden Markov models.

Markov processes.

Stochastic processes.

Genre:

Educational films.

Instructional films.

Physical Description:

1 online resource (41 minutes)

Place of Publication:

Dordrecht, South Holland : Springer Nature, 2022.

Language Note:

In English.

System Details:

video file

Summary:

This video gives an overview of Hidden Markov Models and places them in the context of today's popular data modeling methods. First, the assumptions underlying the hidden Markov model (HMM) are explained, illustrating their usage for prediction and filtering of sequential data. The lecturer provides context when HMMs are useful in comparison to other related approaches such as recurrent neural networks. Finally, an overview of the basic algorithms for performing inference with HMMs and learning their parameters are provided. Watch this video to learn how to model noisy sequences using a classical but highly effective modeling approach.

Notes:

Title from resource description page (viewed January 31, 2023).

OCLC:

1369591520