MACHINE LEARNING

As we have seen in Terminator series that machine takes over the Humans, same in the matrix series also. Did you ever thought can this be ever possible? If yes then how we will gonna control that change?Did you ever thought that how script writers can think something like that without being known to all this?

Well this all  can possible with AI(Artificial Intelligence) or now days it's called as Machine Learning. Machine Learning is the new concept by which machine can learn human behavior and provide information as per requirement and they can change their behavior person to person. So big question is that how they can do that?

This is concept completely related to Human Brain. Human Brain is the most complex structure to understand. Scientist isn't able to understand completely, as they tries to resolve mystery of this, they find something new in this segment. According to research analysis our brain consist of 10 billion's of neural network or it can be more. So just imagine how complex it is to understand. New research says that on an average human uses only 5 to 7% their total brain capacity, brilliant persons can use 20% of their total capacity and an olympic gold medalist uses upto 40% of their total capacity. So, 60% of brain is never used by any human being, it makes me speechless if i just think if any human can reach to 100 % capacity then what are things that he can do?

So what we know right now from this research if we implement it on to the machine, then they can think for any work, understand it, modify it. This will make everything error less.

Machine learning is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed. Machine learning focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data. 

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.

The computational analysis of machine learning algorithms and their performance is a branch of theoretical computer science known as computational learning theory. Because training sets are finite and the future is uncertain, learning theory usually does not yield guarantees of the performance of algorithms. Instead, probabilistic bounds on the performance are quite common. The bias–variance decomposition is one way to quantify generalization error.

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.

Facebook's News Feed uses machine learning to personalize each member's feed. If a member frequently stops scrolling in order to read or "like" a particular friend's posts, the News Feed will start to show more of that friend's activity earlier in the feed. Behind the scenes, the software is simply using statistical analysis and predictive analytics to identify patterns in the user's data and use to patterns to populate the News Feed. Should the member no longer stop to read, like or comment on the friend's posts, that new data will be included in the data set and the News Feed will adjust accordingly.