Machine Learning is all how we train a model using the training data-set. So, the model we train should reflect our training data-set and that is most common challenging part, as the model should not be over-fitted as well as under-fitted. Let us discuss about over-fitting and under-fitting in a different blog, here we shall see what is a BIAS and VARIANCE in machine learning.
We build our machine learning model using our training data, but can we predict the future based on your training data alone or do we need to generalize its ways, patterns to better absorb new data?
This trade-off is captured in "Bias versus Variance".
BIAS : It is the gap between what the model predicted and the actual value.
VARIANCE : It describes how the data is being spread of the predictions.
Put together, bias and variance affect the model's prediction accuracy and can lead to problems with under-fitting and over-fitting.
I read a post in Instagram, which described the BIAS and VARIANCE using a shooting target. It made me to understand, what BIAS and VARIANCE will lead to our end results of the machine learning model we build.
Top comments (0)