Number of Parameters:How LSTM Parmeter Num is Computed.

Here we have defined, The LSTM layers with ten nodes. So let's execute. Okay, and then we can see here in the last column, here the number of parameters. And we see that for the first LSTM layer, we have 480 parameters and for the second LSTM layer, we have even more, 840. So let's see if we increase the number of nodes to 20, what is going on. So now we have even more. So the first LSTM layer has 1,760 parameters, and the second LSTM layer has 3,280 parameters. So where all those figures are coming from? So let's have a look. What we have here is each LSTM node has three gates. So we have an input gate, Sorry. We have a forgotten the gate and we have an output gate.

The initial lectures series on this topic can find in the below links: Introduction to Anomaly Detection https://www.youtube.com/watch?v=IFHX4HUAo1w&list=PLpW3QouFxOnM6YWVOrcUBaQiy8EWi05pi&index=37

How to implement an anomaly detector (1/2) https://www.youtube.com/watch?v=DN0H2Qz3Rxg How to implement an anomaly detector (2/2) https://www.youtube.com/watch?v=nYZuQg5K22Y How to deploy a real-time anomaly detector https://www.youtube.com/watch?v=LnPrT-IkzNw Introduction to Time Series Forecasting https://www.youtube.com/watch?v=G7_uNCOFEzE Stateful vs. Stateless LSTMs https://www.youtube.com/watch?v=R7CwkhZYJdU Batch Size! which batch size is to choose? https://www.youtube.com/watch?v=wfyErdPsZPI Number of Time Steps, Epochs, Training and Validation https://www.youtube.com/watch?v=tsprdX9RkRg Batch size and Trainin Set Size https://www.youtube.com/watch?v=5kLLKhNJlEY Input and Output Data Construction https://www.youtube.com/watch?v=zCHrQRlu688 Designing the LSTM network in Keras https://www.youtube.com/watch?v=Y3ApYArvBr8 Anatomy of a LSTM Node https://www.youtube.com/watch?v=WrA3LlKAbf0 ... https://www.youtube.com/watch?v=oXNBR0U1A54