Tokenization is breaking down a big chunk of text into smaller chunks. Whether it is breaking the paragraph into sentences or sentences into words or words into characters. Tokenization can be very well done using NLTK library.
Activation functions are mathematical equations that determine the output of a neural network. This functions are added to each neuron in the neural network and determines whether it should be fired or not, based on neuron’s input.
There are mainly two types of activation functions
This problem mainly occurs when there is large number of layers in the neural network. As from the previous blog we understood that weights in deep neural networks are updated using the equation as shown
let's mark this equation as equation no. 1
during the back propagation.
Gradient descent is the core of machine learning and it is mainly is used while training the model. In deep learning when you give the input to the neural network it tries to predict the output using the input and the below equation
Have you ever faced an issue of overfitting a situation where your model performs well in you training dataset but performs poorly in you testing dataset?
If yes, then regularization can help you to come out of this issue.
Bias is a gap between the predicted and actual value.
High bias means high gap and Low bias means low gap.
A model with a high bias pays little attention to the training dataset and it oversimplifies the model.
Which in turn leads to high error in both training and testing dataset.
In Machine learning each feature or columns is called as dimension. Reducing the number of column or feature is called as a dimension reduction. Dimension reduction is important because it helps our model to predict more accurate output as it gets less confused.
Scaling down the feature is very much important because if we don’t scale down the values the value of the Euclidian distance Gradient descent will also increases.
Hypothesis testing is done to evaluate two mutually exclusive statements which means either one of the statements can be true on a population data using a sample data.
The binomial distribution model allows us to compute the probability of observing a specified number of "successes" when the process is repeated a specific number of times (e.g. in a set of students grade) and the outcome for a given student's grade is either a success or a failure.
