Home Admin
Home Admin





Machine Learning : What is Machine Learning ?

Machine Learning : What is Machine Learning ?

ravishrks in-community ArtificialIntelligence in-series Age of A.I Jun 27

Machine learning is a method used to make complex models and algorithms by analysing huge amount of data, that lend themselves to prediction , making use of computers.


Card image


It has strong relation with mathematics. Which optimizes and delivers methods, theory and application domains to this field.

It is sometimes conflated with data mining, whereas Data Mining is process where intelligent methods are applied to extract data patterns.

Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. This definition of the tasks in which machine learning is concerned offers a fundamentally operational definition rather than defining the field in cognitive terms.

If we talk about tasks of Machine Learning. Let's have a look below.

Supervised learning: In Supervised learning the computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that gives desired outputs.

It is where you have input variables (x) and an output variable (Y) and you use an algorithm to learn the mapping function from the input to the output.

In Reinforcement learning data is trained in form of rewards and punishments and is given only as feedback to the program's actions in a dynamic environment.

If we go informal to Reinforcement learning . Think about the first time you were able to drive your bicycle. No one can instruct you the every aspect of driving bicycle. You learn it by your own, 'subconsciously' by practicing regularly. You learn how to balance bicycle after various attempts. Its the same type of process computers use to learn things, such as balancing something or targeting goals.

A core objective of a learner is to generalize from its experience. Generalization in this context is the ability of a learning machine to perform accurately on new, unseen examples/tasks after having experienced a learning data set.

The training examples come from some generally unknown probability distribution (considered representative of the space of occurrences) and the learner has to build a general model about this space that enables it to produce sufficiently accurate predictions in new cases.

For the best performance in the context of generalization, the complexity of the hypothesis should match the complexity of the function underlying the data. If the hypothesis is less complex than the function, then the model has underfit the data. If the complexity of the model is increased in response, then the training error decreases. But if the hypothesis is too complex, then the model is subject to overfitting and generalization will be poorer.

In addition to performance bounds, computational learning theorists study the time complexity and feasibility of learning. In computational learning theory, a computation is considered feasible if it can be done in polynomial time. There are two kinds of time complexity results. Positive results show that a certain class of functions can be learned in polynomial time. Negative results show that certain classes cannot be learned in polynomial time.

Although machine learning has been very transformative in some fields, effective machine learning is difficult because finding patterns is hard and often not enough training data are available; as a result, machine-learning programs often fail to deliver.




Comments




Read next...



Sujjested Posts...


Machine Learning : What is Machine Learning ?

Machine learning is a metho ...

Generic placeholder image

Journey to Artificial Intelligence

Today, A.I dominates in every ...

Generic placeholder image