Presentation is loading. Please wait.

Presentation is loading. Please wait.

LSTM Practical Exercise

Similar presentations


Presentation on theme: "LSTM Practical Exercise"β€” Presentation transcript:

1 LSTM Practical Exercise
R. Q. Feitosa, J. D. Bermudez, J. A. Chamorro

2 Objective Predict the value of 𝑋 𝑑+1 from past observations ( 𝑋 π‘‘βˆ’2 , 𝑋 π‘‘βˆ’1 , 𝑋 𝑑 )

3 Network Architecture Architecture: Many-to-one LSTM

4 Dataset Daily USD to BRL exchange rate from April 30th 2018 to April 30th 2019.

5 Dataset Daily USD to BRL exchange rate from April 30th 2018 to April 30th 2019.
Train Test

6 Dataset Dataset preprocessing: Sliding window
𝒙 𝟏 𝒙 𝟐 𝒙 πŸ‘ y 3.92 3.99 3.9 3.86 Train Test

7 Dataset Dataset preprocessing: Sliding window
𝒙 𝟏 𝒙 𝟐 𝒙 πŸ‘ y 3.92 3.99 3.9 3.86 3.89 Train Test

8 Dataset Dataset preprocessing: Sliding window
𝒙 𝟏 𝒙 𝟐 𝒙 πŸ‘ 𝑦 3.92 3.99 3.9 3.86 3.89 … Train Test

9 Experimental setup Network architecture: LSTM (Many-to-one)

10 Expected Results Root Mean Squared Error Train: 0.02939 Test: 0.03424
Train prediction results Test prediction results

11 Exercises Exercise 1: Exercise 2:
Define the LSTM network architecture according to this presentation Exercise 2: Evaluate the network performance in terms of RMSE and prediction graph for the next configuration modifications: 10 and 100 epochs 10 and 100 LSTM hidden units 2 LSTM layers (Deep LSTM) Use GRU instead of LSTM


Download ppt "LSTM Practical Exercise"

Similar presentations


Ads by Google