Explore
For Enterprise
Join for Free
Log In

Explorar
Buscar
For Enterprise
Inicia Sesión
Únete de forma gratuita

Train, validation and test sets

Loading...

Sequences, Time Series and Prediction

deeplearning.ai

4.6 (674 calificaciones) | 12K estudiantes inscritos

Curso 4 de 4 en TensorFlow in Practice Programa Especializado

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This Specialization will teach you best practices for using TensorFlow, a popular open-source framework for machine learning. In this fourth course, you will learn how to build time series models in TensorFlow. You’ll first implement best practices to prepare time series data. You’ll also explore how RNNs and 1D ConvNets can be used for prediction. Finally, you’ll apply everything you’ve learned throughout the Specialization to build a sunspot prediction model using real-world data! The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Destrezas que aprenderás

Forecasting, Machine Learning, Tensorflow, Time Series, prediction

Revisiones

4.6 (674 calificaciones)

5 stars
500 ratings
4 stars
121 ratings
3 stars
34 ratings
2 stars
8 ratings
1 star
11 ratings

PS

Sep 14, 2019

An excellent course on Time Series and Sequences by Laurence Moroney. Explained how to use CNN, RNN and DNN together to bring the nest out of time series prediction.

GG

Aug 05, 2019

Fantastic course, starting from basic fundamentals of statistical forecasting to using Convolutional neural networks. I will use my learnings directly to my job.

De la lección

Sequences and Prediction

Hi Learners and welcome to this course on sequences and prediction! In this course we'll take a look at some of the unique considerations involved when handling sequential time series data -- where values change over time, like the temperature on a particular day, or the number of visitors to your web site. We'll discuss various methodologies for predicting future values in these time series, building on what you've learned in previous courses!

Time series examples4:04

Machine learning applied to time series1:55

Common patterns in time series5:05

Introduction to time series4:33

Train, validation and test sets3:21

Metrics for evaluating performance2:20

Moving average and differencing2:45

Trailing versus centered windows1:00

Forecasting4:36

Impartido por:

Laurence Moroney
AI Advocate

Transcripción

In the previous videos this week, you saw all of the different factors that make up the behavior of a time series. Now we'll start looking at techniques, given what we know, that can be used to then forecast that time series. Let's start with this time series containing, trend seasonality, and noise and that's realistic enough for now. We could, for example, take the last value and assume that the next value will be the same one, and this is called naive forecasting. I've zoomed into a part of the data set here to show that in action. We can do that to get a baseline at the very least, and believe it or not, that baseline can be pretty good. But how do you measure performance? To measure the performance of our forecasting model,. We typically want to split the time series into a training period, a validation period and a test period. This is called fixed partitioning. If the time series has some seasonality, you generally want to ensure that each period contains a whole number of seasons. For example, one year, or two years, or three years, if the time series has a yearly seasonality. You generally don't want one year and a half, or else some months will be represented more than others. While this might appear a little different from the training validation test, that you might be familiar with from non-time series data sets. Where you just picked random values out of the corpus to make all three, you should see that the impact is effectively the same. Next you'll train your model on the training period, and you'll evaluate it on the validation period. Here's where you can experiment to find the right architecture for training. And work on it and your hyper parameters, until you get the desired performance, measured using the validation set. Often, once you've done that, you can retrain using both the training and validation data. And then test on the test period to see if your model will perform just as well. And if it does, then you could take the unusual step of retraining again, using also the test data. But why would you do that? Well, it's because the test data is the closest data you have to the current point in time. And as such it's often the strongest signal in determining future values. If your model is not trained using that data, too, then it may not be optimal. Due to this, it's actually quite common to forgo a test set all together. And just train, using a training period and a validation period, and the test set is in the future. We'll follow some of that methodology in this course. Fixed partitioning like this is very simple and very intuitive, but there's also another way. We start with a short training period, and we gradually increase it, say by one day at a time, or by one week at a time. At each iteration, we train the model on a training period. And we use it to forecast the following day, or the following week, in the validation period. And this is called roll-forward partitioning. You could see it as doing fixed partitioning a number of times, and then continually refining the model as such. For the purposes of learning time series prediction in this course, will learn the overall code for doing series prediction. Which you could then apply yourself to a roll-forward scenario, but our focus is going to be on fixed partitioning.

Explora nuestro catálogo

Inscríbete de manera gratuita y obtén recomendaciones personalizadas, actualizaciones y ofertas.

Coursera brinda acceso universal a la mejor educación del mundo, al asociarse con las mejores universidades y organizaciones, para ofrecer cursos en línea.

© 2019 Coursera Inc. Todos los derechos reservados.

Consíguelo en Google Play

Coursera
Acerca de
Liderazgo
Empleo
Catálogo
Certificados
Certificados MasterTrack™
Grados
For Enterprise
For Government
Para el campus

Comunidad
Learners
Partners
Developers
Beta Testers
Translators

Conectar
Blog
Facebook
LinkedIn
Twitter
Instagram
Youtube
Blog de Tecnología

Más
Términos
Privacidad
Ayuda
Accesibilidad
Prensa
Contacto
Directorio
Afiliados