Machine Learning is all about learning from examples. Real world is messy, hard logical rules are not the way to solve real world problems

Rather than writing 100s and 1000s line of codes, instead have the machines learn from observations of the world and insert it in the algorithm. Maybe millions, billions or trillions of information, identifying the patterns and generalise from there.

Machine Learning Model/Sub-Fields – 

Pattern Recognition- Pattern recognition can be defined as the classification of data based on knowledge already gained or on statistical information extracted from patterns and/or their representation.

 

Artificial Neural Network- Artificial neural networks are computing systems vaguely inspired by the biological neural networks that constitute animal brains. Such systems “learn” to perform tasks by considering examples, generally without being programmed with task-specific rules.

 

Reinforcement Learning- Reinforcement learning is an area of machine learning concerned with how software agents ought to take actions in an environment in order to maximize some notion of cumulative reward. 

Statistical Inference- Statistical inference is the process of using data analysis to deduce properties of an underlying probability distribution.

Probabilistic Machine Learning- The key idea behind the probabilistic framework to machine learning is that learning can be thought of as inferring plausible models to explain observed data. A machine can use such models to make predictions about future data, and take decisions that are rational given these predictions.

Supervised Learning- Supervised learning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs

Unsupervised Learning- Unsupervised learning is a machine learning technique, where you do not need to supervise the model. Instead, you need to allow the model to work on its own to discover information. It mainly deals with the unlabelled data.

 

Ensemble Algorithms- Ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone.

Structured Prediction- Structured prediction uses supervised machine learning techniques that involves predicting structured objects, rather than scalar discrete or real values.

Clustering- Clustering is the task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups.

So in Machine learning we take a particular problem and spread it out over lots and lots of machines, a very important approach because it makes our research faster .

Some Applications for  MACHINE LEARNING/A.I. – 

• Anti lock braking
• Autopilot systems for planes
• Search
• Recommendations
• Maps
• To decide whether or not a particular mail is spam or not spam
• Translator programs (Language)
• Voice Search 
•  

Machine Learning Examples: How it works:-

In task of Image Recognition

Take pictures and Train Machine learning models to take pixels of an image,and from those pixels, learn High level features like : – art, joy, child,birthday,party,day. If the Program see a birthday cake, lots of kids, (from the point of view of humans). That’s essentially teaching the machine what to do, the perceptions that we humans are so natural and so good at.

In field of Speech Recognition

To teach speech recognition, try to interact with in a noisy room, we used real world sound and we mix it into the other examples that we already have. Now, no matter what the noise is in the environment, our speech recognition systems can understand what we are saying, separate out one speaker from the other. With Machine learning we have an algorithm that learns how to stimulate a human linguist.

We hope you understand how Machine Learning is all about learning from examples and that this blog helped you understand Machine Learning better!