In this project, we will analyze various sequential data types like text streams, audio clips, time-series data, and genetic data, and understand pre-processing techniques associated with each.
Sequential modelling is the process of forecasting a sequence of values from a set of input values. Input values can contain elements that are ordered into sequences like time series, text streams, or DNA sequences. A lot of tasks can be modelled from these types of data. For example:
- text classification, e.g. spam email or not
- language translation, e.g. French to English
- time-series forecasting, e.g. stock price prediction
In this project, i learnt
- Describe various forms of sequential data, and common tasks that can be modelled using sequential data
- Decompose a time-series and perform time-series imputation
- Pre-process and vectorize a text stream and genetic dataset
- Pre-process and visualize an audio dataset, and create spectrograms