Hello :) Today is Day 21!
A quick summary of today:
- finished the DeepLearning AI course that prepares me for the certificate
However, I don’t think I can take the actual test yet. Because I think I need more practice. From tomorrow, I will apply what I learned in the course as the data I see in kaggle.
Today I finished the last part - Sequences, Time series & Prediction
I found the code for a very useful function
When predicting time series with tensorflow, the dataset must be divided into windows
You can train with this simple model, but it might be too simple
I learned about the Huber loss - In statistics, the Huber loss is a loss function used in robust regression, that is less sensitive to outliers in data than the squared error loss
You have to change the data to the lambda layer before dividing it into windows and putting it into the Bidirectional LSTM layer. In addition, x*100.0 is applied to change it to a more understandable type in the last layer
In the last piece of homework, I made the below model
results: mse: 5.34, mae: 1.80
- Certificate
I also found a recent talk by Andrew Ng on opporunities in AI
The full color is in the current state, but the semi-transparent color is in the state of AI after 3 years.
That is all for today!
See you tomorrow :)