課程信息
161,797 次近期查看

第 4 門課程(共 4 門)

100% 在線

立即開始,按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

You should take the first 3 courses of the TensorFlow Specialization and be comfortable coding in Python and understanding high school-level math.

完成時間大約為8 小時

建議:4 weeks of study, 4-5 hours/week...

英語(English)

字幕:英語(English)

您將學到的內容有

  • Check

    Solve time series and forecasting problems in TensorFlow

  • Check

    Prepare data for time series learning using best practices

  • Check

    Explore how RNNs and ConvNets can be used for predictions

  • Check

    Build a sunspot prediction model using real-world data

您將獲得的技能

ForecastingMachine LearningTensorflowTime Seriesprediction
學習Course的學生是
  • Data Scientists
  • Machine Learning Engineers
  • Traders
  • Data Engineers
  • Biostatisticians

第 4 門課程(共 4 門)

100% 在線

立即開始,按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

You should take the first 3 courses of the TensorFlow Specialization and be comfortable coding in Python and understanding high school-level math.

完成時間大約為8 小時

建議:4 weeks of study, 4-5 hours/week...

英語(English)

字幕:英語(English)

教學大綱 - 您將從這門課程中學到什麼

1
完成時間為 3 小時

Sequences and Prediction

10 個視頻 (總計 33 分鐘), 3 個閱讀材料, 3 個測驗
10 個視頻
Time series examples4分鐘
Machine learning applied to time series1分鐘
Common patterns in time series5分鐘
Introduction to time series4分鐘
Train, validation and test sets3分鐘
Metrics for evaluating performance2分鐘
Moving average and differencing2分鐘
Trailing versus centered windows1分鐘
Forecasting4分鐘
3 個閱讀材料
Introduction to time series notebook10分鐘
Forecasting notebook10分鐘
Week 1 Wrap up10分鐘
1 個練習
Week 1 Quiz
2
完成時間為 3 小時

Deep Neural Networks for Time Series

10 個視頻 (總計 27 分鐘), 5 個閱讀材料, 3 個測驗
10 個視頻
Preparing features and labels4分鐘
Preparing features and labels3分鐘
Feeding windowed dataset into neural network2分鐘
Single layer neural network2分鐘
Machine learning on time windows37
Prediction2分鐘
More on single layer neural network2分鐘
Deep neural network training, tuning and prediction4分鐘
Deep neural network3分鐘
5 個閱讀材料
Preparing features and labels notebook10分鐘
Sequence bias10分鐘
Single layer neural network notebook10分鐘
Deep neural network notebook10分鐘
Week 2 Wrap up10分鐘
1 個練習
Week 2 Quiz
3
完成時間為 3 小時

Recurrent Neural Networks for Time Series

10 個視頻 (總計 20 分鐘), 5 個閱讀材料, 3 個測驗
10 個視頻
Conceptual overview2分鐘
Shape of the inputs to the RNN2分鐘
Outputting a sequence1分鐘
Lambda layers1分鐘
Adjusting the learning rate dynamically2分鐘
RNN1分鐘
LSTM1分鐘
Coding LSTMs2分鐘
More on LSTM1分鐘
5 個閱讀材料
More info on Huber loss10分鐘
RNN notebook10分鐘
Link to the LSTM lesson10分鐘
LSTM notebook10分鐘
Week 3 Wrap up10分鐘
1 個練習
Week 3 Quiz
4
完成時間為 3 小時

Real-world time series data

11 個視頻 (總計 24 分鐘), 5 個閱讀材料, 3 個測驗
11 個視頻
Convolutions58
Bi-directional LSTMs3分鐘
LSTM1分鐘
Real data - sunspots3分鐘
Train and tune the model3分鐘
Prediction1分鐘
Sunspots1分鐘
Combining our tools for analysis3分鐘
Congratulations!38
Specialization wrap up - A conversation with Andrew Ng2分鐘
5 個閱讀材料
Convolutional neural networks course10分鐘
More on batch sizing10分鐘
LSTM notebook10分鐘
Sunspots notebook10分鐘
Wrap up10分鐘
1 個練習
Week 4 Quiz
4.6
112 個審閱Chevron Right

來自Sequences, Time Series and Prediction的熱門評論

創建者 ORAug 4th 2019

It was an amazing experience to learn from such great experts in the field and get a complete understanding of all the concepts involved and also get thorough understanding of the programming skills.

創建者 YKSep 30th 2019

A step by step explanation of how to use TensorFlow 2.0 for building a Neural network for sequences and time series. With detailed examples of code and of how to choose hyper-parameters.

講師

Avatar

Laurence Moroney

AI Advocate
Google Brain

關於 deeplearning.ai

deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders....

關於 TensorFlow in Practice 專項課程

Discover the tools software developers use to build scalable AI-powered algorithms in TensorFlow, a popular open-source machine learning framework. In this four-course Specialization, you’ll explore exciting opportunities for AI applications. Begin by developing an understanding of how to build and train neural networks. Improve a network’s performance using convolutions as you train it to identify real-world images. You’ll teach machines to understand, analyze, and respond to human speech with natural language processing systems. Learn to process text, represent sentences as vectors, and input data to a neural network. You’ll even train an AI to create original poetry! AI is already transforming industries across the world. After finishing this Specialization, you’ll be able to apply your new TensorFlow skills to a wide range of problems and projects. Courses 1-3 are available now, with Course 4 launching in July....
TensorFlow in Practice

常見問題

  • 注册以便获得证书后,您将有权访问所有视频、测验和编程作业(如果适用)。只有在您的班次开课之后,才可以提交和审阅同学互评作业。如果您选择在不购买的情况下浏览课程,可能无法访问某些作业。

  • 您注册课程后,将有权访问专项课程中的所有课程,并且会在完成课程后获得证书。您的电子课程证书将添加到您的成就页中,您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容,可以免费旁听课程。

還有其他問題嗎?請訪問 學生幫助中心