Journey of Curiosity
When we do the training we divide the data into two sets, train and test. this is called a hold-out set where we keep some data outside the training. This way we prevent the model from learning the test dataset. However, this method is not useful everywhere. Choosing the right cross-validation is very important as the different datasets may require different cross-validations.
Why do we need precision and recall? How do we get f1 score? what does f1 score represent? We will answer all of these questions.
Building a sarcasm detection model using natural language processing is easier than you think. This can be your first project for NLP.
Why do we use ReLU activation function over sigmoid or tanh? Why activation functions suffer from vanishing gradient problem?
What is an activation function?
What is linearity or non-linearity?
Why do we use a non-linear activation function?
Understand the Branch and bound algorithm and then then step up to learn A* algorithm.