Dafne van Kuppevelt | Deep learning for time series made easy
PyData Amsterdam 2017
Deep learning is a state of the art method for many tasks, such as image classification and object detection. For researchers that have time series data, but are not an expert on deep learning, the barrier can be high to start using deep learning. We developed mcfly, an open source python library, to help machine learning novices explore the value of deep learning for time series data.
In this talk, we will explore how machine learning novices can be aided in the use of deep learning for time series classification.
In a variety of scientific fields researchers face the challenge of time series classification. For example, to classify activity types from wrist-worn accelerometer data or to classify epilepsy from electroencephalogram (EEG) data. For researchers who are new to the field of deep learning, the barrier can be high to start using deep learning. In contrast to computer vision use cases, where there are tools such as caffe that provide pre-defined models to apply on new data, it takes some knowledge to choose an architecture and hyperparameters for the model when working with time series data.
We developed mcfly, an open source python library to make time series classification with deep learning easy. It is a wrapper around Keras, a popular python library for deep learning. Mcfly provides a set of suitable architectures to start with, and performs a search over possible hyper-parameters to propose a most suitable model for the classification task provided. We will demonstrate mcfly with excerpts from (multi-channel) time series data from movement sensors that are associated with a class label, namely activity type (sleeping, walking, climbing stairs). In our example, mcfly will be used to train a deep learning model to label new data. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps
Видео Dafne van Kuppevelt | Deep learning for time series made easy канала PyData
Deep learning is a state of the art method for many tasks, such as image classification and object detection. For researchers that have time series data, but are not an expert on deep learning, the barrier can be high to start using deep learning. We developed mcfly, an open source python library, to help machine learning novices explore the value of deep learning for time series data.
In this talk, we will explore how machine learning novices can be aided in the use of deep learning for time series classification.
In a variety of scientific fields researchers face the challenge of time series classification. For example, to classify activity types from wrist-worn accelerometer data or to classify epilepsy from electroencephalogram (EEG) data. For researchers who are new to the field of deep learning, the barrier can be high to start using deep learning. In contrast to computer vision use cases, where there are tools such as caffe that provide pre-defined models to apply on new data, it takes some knowledge to choose an architecture and hyperparameters for the model when working with time series data.
We developed mcfly, an open source python library to make time series classification with deep learning easy. It is a wrapper around Keras, a popular python library for deep learning. Mcfly provides a set of suitable architectures to start with, and performs a search over possible hyper-parameters to propose a most suitable model for the classification task provided. We will demonstrate mcfly with excerpts from (multi-channel) time series data from movement sensors that are associated with a class label, namely activity type (sleeping, walking, climbing stairs). In our example, mcfly will be used to train a deep learning model to label new data. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps
Видео Dafne van Kuppevelt | Deep learning for time series made easy канала PyData
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Jeffrey Yau: Time Series Forecasting using Statistical and Machine Learning Models | PyData NYC 2017](https://i.ytimg.com/vi/_vQ0W_qXMxk/default.jpg)
![PyCon.DE 2017 Nils Braun - Time series feature extraction with tsfresh - “get rich or die..](https://i.ytimg.com/vi/Fm8zcOMJ-9E/default.jpg)
![Deep Learning for Video Analysis - Victor Campos - UPC Barcelona 2018](https://i.ytimg.com/vi/dY7j5dBqS5g/default.jpg)
![State of the Art Convolutional Neural Networks (CNNs) Explained | Deep Learning in 2020](https://i.ytimg.com/vi/YUyec4eCEiY/default.jpg)
![Jeremy Tuloup: JupyterLite: Jupyter ❤️ WebAssembly ❤️ Python](https://i.ytimg.com/vi/4rDRs_W9ICM/default.jpg)
![Data Science 101: Deploying your Machine Learning Model](https://i.ytimg.com/vi/jMrp6XfYIyk/default.jpg)
![](https://i.ytimg.com/vi/e37GOzb1krk/default.jpg)
![Igor Gotlibovych: Deep Learning and Time Series Forecasting for Smarter Energy | PyData London 2019](https://i.ytimg.com/vi/p6mKFs6HVlg/default.jpg)
![Introduction to Forecasting in Machine Learning and Deep Learning](https://i.ytimg.com/vi/bn8rVBuIcFg/default.jpg)
![Bayesian Statistics Made Simple | Scipy 2019 Tutorial | Allen Downey](https://i.ytimg.com/vi/-X0BiV9n_fQ/default.jpg)
![1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jeff Roach](https://i.ytimg.com/vi/nMkqWxMjWzg/default.jpg)
![Time Series Analysis with Python Intermediate | SciPy 2016 Tutorial | Aileen Nielsen](https://i.ytimg.com/vi/JNfxr4BQrLk/default.jpg)
![Video Classification with Deep Learning](https://i.ytimg.com/vi/LAV56E-mWoo/default.jpg)
![Autoencoder Forest for Anomaly Detection from IoT Time Series | SP Group](https://i.ytimg.com/vi/V0r2zDhdi6c/default.jpg)
![Looking beyond LSTMs: Alternatives to Time Series Modelling using Neural Nets - Aditya Patel](https://i.ytimg.com/vi/WoLlZLdoEQk/default.jpg)
![Deep Learning for Time Series Data (O'Reilly Artificial Intelligence Conference)](https://i.ytimg.com/vi/aXPh0NWNfcc/default.jpg)
![CNNLSTM timeseries Eversmann](https://i.ytimg.com/vi/lmk_EYG0vDI/default.jpg)
![Unsupervised Anomaly Detection with Isolation Forest - Elena Sharova](https://i.ytimg.com/vi/5p8B2Ikcw-k/default.jpg)
![Samuel Rochette: Quantifying uncertainty in machine learning models | PyData New York 2019](https://i.ytimg.com/vi/yk5cmVW3EA0/default.jpg)
![When Do You Use Machine Learning vs. a Rules Based System?](https://i.ytimg.com/vi/yjy90pdBLfo/default.jpg)