Beginning Anomaly Detection Using

 Anomaly Detection with the ED-TCN

Let’s put this model to the test by applying it to the credit card dataset. Once again, this 

example is another instance of 

supervised learning, so you will have both anomalies 

and normal data labeled.

First, begin by importing all of the necessary modules (see Figure 

7-53

).

4   2   

6

7   1   6   9   5

4   4   2   2

6   6

Figure 7-51.  This process is repeated with the third entry in the input vector to 

form the next third pair of entries in the output vector

4   2   6   7   1   6   9   5

4   4   2   2   6   6   7   7   1   1   6   6   9   9   5   5 

Figure 7-52.  The output vector after the upsampling operation compared to the 

original input vector below it

Chapter 7   temporal Convolutional networks

---

287

Next, load your data and preprocess it. Notice that the steps are basically the same as 

in the first example (see Figure 

7-54

).