1-844-696-6465 (US)        +91 77600 44484        help@dezyre.com
time-series-forecasting-deep-learning.jpg

Time Series Forecasting with LSTM Neural Network Python

Deep Learning Project- Learn to apply deep learning paradigm to forecast univariate time series data.
4.74.7

Users who bought this project also bought

What will you learn

  • How to develop a baseline of performance for a forecast problem.
  • How to design a robust test harness for one-step time series forecasting.
  • How to prepare data for LSTM recurrent neural network python model
  • How to develop LSTM python model
  • How to evaluate an LSTM recurrent neural network for time series forecasting.

What will you get

  • Access to recording of the complete project
  • Access to all material related to project like data files, solution files etc.

Prerequisites

  • Jupyter Notebook from Anaconda installation
  • R and R-Studio installation
  • At least 5MBS internet speed
  • At least 4 GB RAM Machine

Project Description

Deep learning is an upcoming field, where we are seeing a lot of implementations in the day to day business operations, including segmentation, clustering, forecasting, prediction or recommendation etc. Deep learning architecture has many branches and one of them is the recurrent neural network (RNN), the method that we are going to analyze in this deep learning project is about Long Short Term Memory Network (LSTM) to perform time series forecasting for univariate time series data.

Instructors

 
Pradeepta

Curriculum For This Mini Project

 
  Deep Learning Architectures
00:06:46
  DNN - Deep Neural Network
00:00:30
  CNN - Convolutional Neural Network
00:01:29
  RNN - Recurrent Neural Network
00:02:22
  Deep Belief & Boltzman Network
00:01:04
  Deep Neural Network - Graphical Representation
00:20:09
  Activation Functions
00:02:51
  Perceptron and Bias
00:02:51
  Convolutional Neural Network - Graphical Representation
00:08:13
  Recurrent Neural Network - Graphical Representation
00:07:06
  Deep Belief & Boltzman Network - Graphical Representation
00:00:58
  Problem Statement
00:01:17
  Data Set
00:05:31
  Setting up Libraries
00:15:27
  Setting Theano as backend
00:01:17
  Import Libraries
00:02:49
  Create Seed function
00:01:55
  Normalize the dataset
00:04:26
  Split dataset into training and testing
00:06:19
  Create Dataset Matrix
00:07:16
  Reshape Dataset
00:05:04
  Create RNN or LSTM Model
00:04:11
  Make Predictions
00:08:09
  Calculate Mean Squared Error
00:03:53
  Conclusion
00:05:36