A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Apache License 2.0
27.26k
stars
12.6k
forks
source link
[QUESTION] Chapter 1: How reducing the number of features of training data effects overfitting? #578
In second edition of this book,
In page no 28,
While discussing about overfitting,
In the text book, it is given as:
Simplify the model by selecting one with fewer parameters
(e.g., a linear model rather than a high-degree polynomial
model), by reducing the number of attributes in the training
data, or by constraining the model.
In the above paragraph, I didn't understand how reducing the number of attributes in the training data will simply the model?
and how this controls the overfitting?
I misunderstood the sentence.
Its actually by reducing the attributes of the data we can reduce the parameters of the model and thus simplifying the model.
In second edition of this book, In page no 28, While discussing about overfitting,
In the text book, it is given as:
In the above paragraph, I didn't understand how reducing the number of attributes in the training data will simply the model? and how this controls the overfitting?
Thanks in advance :)