9 Gedanken zu „Time frame Group Foretelling of with LSTM Deep Getting to know“

  1. very great video. I have a question on predicting the future. I have historical data (2012 to 2017) and I want to predict 2018 to 2020. I get the training and testing part, but do you have a sample code to do the prediction? can I have your email to send you my data? thanks so much in advance.

  2. very great video. I have a question on predicting the future. I have historical data (2012 to 2017) and I want to predict 2018 to 2020. I get the training and testing part, but do you have a sample code to do the prediction? can I have your email to send you my data? thanks so much in advance

  3. Can anyone please tell me how to solve the problem the 'pd' module not found from line from pb import log_progress, please help me , thank you very much.

  4. how do we do prediction in 3 months advance. Eg. i have sales data till today and i want to do prediction for next 3 months . we dont have any information except date field. How will we do prediction using LSTM model

  5. Thanks for this great video. I have two questions:
    1. can you please explain the input_shape and the reshape part. Here data is of the shape (num_examples, 7). Why do we reshape it as (num_examples, 1, 7). Keras documentation says input_shape should be (batch_size, timestep, input_dim). I understand the batch_size and input_dim. batch_size= num_examples(no mini batch) and input_dim = 7. But why is timestep = 1. Does it mean, Keras will go back only 1 step during backpropagation, or does it have to do anything with the lag (5 in this example).

    2. What is the effect of Including features such as is_holiday (which is more or less static and is not a series) compared to t1, t2, etc. How does LSTM distinguish between a features that is series and the one that is stationary?

Schreibe einen Kommentar

Deine E-Mail-Adresse wird nicht veröffentlicht. Erforderliche Felder sind mit * markiert.