Time Series Classification Using Deep Learning
In this article, I will introduce you to a new package called timeseries for fastai2 that I lately developed.
time-series fastai tutorial article code library

The timeseries package allows you to train a Neural Network (NN) model in order to classify both univariate and multivariate time series using the powerful fastai2 library and achieve State Of The Art (SOTA) results.

The key objectives of this series of articles are: • Introduce you to time series classification using Deep Learning, • Show you a step by step how this package was built using fastai2 library, • Introduce you to some key concepts of the fastai2 library such as Datasets, DataLoaders, DataBlock, Transform, etc.

Don't forget to tag @ai-fast-track , @fhassa in your comment, otherwise they may not be notified.

Authors community post
Helping democratize AI/DL. Breaking down complex concepts into easy to understand pieces. PhD - Biomed. Eng. Postdoc - Biomed. Eng. & Neurosciences Created StatMap3D - DataFinder
Share this project
Similar projects
Getting Started with Time Series analysis using Pandas
An introductory guide to get started with the Time Series datasets in Python
STUMPY: A Powerful and Scalable Python Library for Time Series
STUMPY is a powerful and scalable Python library for computing a Matrix Profile, which can be used for a variety of time series data mining tasks.
Timeseries Anomaly Detection using an Autoencoder
Detect anomalies in a timeseries using an Autoencoder.
Entity Embedding with LSTM for Time-Series
Demonstration of using LSTM for forecasting with structured time-series data, containing categorical and numerical features.
Top collections