Generalization in Machine Learning

-
In machine learning, we describe the learning of the target function from training data as inductive learning.
Induction refers to learning general concepts from specific examples which is exactly the problem that supervised machine learning problems aim to solve. This is different from deduction that is the other way around and seeks to learn specific concepts from general rules.
Generalization refers to how well the concepts learned by a machine learning model apply to specific examples not seen by the model when it was learning.
The goal of a good machine learning model is to generalize well from the training data to any data from the problem domain. This allows us to make predictions in the future on data the model has never seen.
There is a terminology used in machine learning when we talk about how well a machine learning model learns and generalizes to new data, namely overfitting and underfitting.
Overfitting and underfitting are the two biggest causes for poor performance of machine learning algorithms.

Comments

Post a Comment

Popular posts from this blog

Hyperparameter tuning for machine learning models.

-
Image
When creating a machine learning model, you'll be presented with design choices as to how to define your model architecture. Often times, we don't immediately know what the optimal model architecture should be for a given model, and thus we'd like to be able to explore a range of possibilities. In true machine learning fashion, we'll ideally ask the machine to perform this exploration and select the optimal model architecture automatically. Parameters which define the model architecture are referred to as  hyperparameters  and thus this process of searching for the ideal model architecture is referred to as  hyperparameter tuning . Whereas the model parameters specify how to transform the input data into the desired output, the hyperparameters define how our model is actually structured. Unfortunately, there's no way to calculate “which way should I update my hyperparameter to reduce the loss?” (ie. gradients) in order to find the optimal model architecture; thu...
Read more

The Difference Between ID and Class in CSS

-
Image
The difference between an ID and a class is that an ID can be used to identify one element, whereas a class can be used to identify more than one. The benefit of this is that you can have the same HTML element, but presented it differently depends upon its class and id properties.  HTML elements can have both class and Id  selectors. <div class = "box"  id = "header">     .............     ............. </div> In the CSS, a class selector is a name preceded by a  full stop  (“.”) and an ID selector is a name preceded by a  hash character  (“#”).    ID's are unique Each Element can has only one id. Each page can have only one element with that ID. CLASSES are Not unique we can use same class on multiple elements we can use multiple class on the same elements
Read more