Skip to main content

What is machine learning and how it works


Machine Learning is a subset of AI uses computer algorithms to analyse data to make intelligent decision based on what it has learnt.Instead following the rule based algorithms machine learning build models to classify and prediction from data.Lets understand this by exploring the problem which can be solve with machine learning.

Suppose that a heart is going to fail or not can be solved by machine learning. So the answer is 'yes'.Let we are giving the data set like BPM (beats per minute),BMI (body mass index),age,sex and result.With machine learning we are able to learn and create models that predicts the result.Machine learning relies on defining the behavioral rules by examining and comparing large dataset to find the common patterns.

For example we can provide the machine learning program with large volume pictures of bird and can train the model to identify the bird label whenever bird input is provided.When a picture of bird is provided to the machine learning model.It will show the picture with some confidence this type of learning is called the supervised learning.

Supervised Learning-

An algorithm is trained on the human-labeled data.The more sample you provide the supervised learning algorithm,the more precise it becomes in classifying new data.

Unsupervised Learning-

Unsupervised Learning is another type of machine language which relies algorithm to unlabeled data and letting it find patterns by itself.You provide the input but not labels and let machine infern qualities that algorithm ingest unlabeled data,draws inferences and find patterns.This kind of learning is useful for clustering data where data is grouped how much similar to its neighbour and dissimilar to everything else.Once the data is clustered then different technique can be used to find patterns from
that data.

Reinforcement Learning-

Reinforcement Learning relies on providing a machine learning algorithm with a set of rules and constraints and letting it learn how to achieve its goal.You define the state,desired goal,allowed actions and constraints.The algorithm figures out how achieve the goal by trying different combination of allowed actions and it is rewarded or punish depending on whether the decision was the good one or not.Reinforcement learning can be use to play chess.

Comments

Post a Comment

Popular posts from this blog

What is Artificial Intelligence,its type and applications

AI is a part of Computer Science.AI is anything that makes machine more intelligent. AI is a technology which can not replace human intelligence but rather it can extend human capabilities.Now a days AI is most wanted and powerful technology.Every industry wants to have its AI system because it can process very large amount of data in less time. How does AI learn ? The intelligence which machine having is only provided by us.So basically we provide to machine  ability to examine and create machine learning models based on inputs and desired output and we do this based on supervised learning,unsupervised learning and reinforcement learning. Types of AI based on Strength Weak or Narrow AI- Narrow AI is that applied on specific domain.It can perform specific task but can not learn new things its own.It can only make decision based on programmed algorithms and trained data.For example AI powered based searches,virtual assistant,self driving cars,language translato...
4 comments
Read more

ANN in depth

Artificial Neural Network Layers Artificial Neural network is typically organized in layers. Layers are being made up of many interconnected ‘nodes’ which contain an  ‘activation function’.  A neural network may contain the following 3 layers: a. Input layer The purpose of the input layer is to receive as input the values of the explanatory attributes for each observation. Usually, the number of input nodes in an input layer is equal to the number of explanatory variables. ‘input layer’ presents the patterns to the network, which communicates to one or more ‘hidden layers’. The nodes of the input layer are passive, meaning they do not change the data. They receive a single value on their input and duplicate the value to their many outputs. From the input layer, it duplicates each value and sent to all the hidden nodes. b. Hidden layer The  Hidden layers  apply given transformations to the input values inside the network. In this, incoming arcs that go...
Post a Comment
Read more

5 machine learning applications

Artificial Intelligence (AI) is everywhere. Possibility is that you are using it in one way or the other and you don’t even know about it. One of the popular applications of AI is Machine Learning (ML), in which computers, software, and devices perform via cognition (very similar to human brain). Herein, we share few examples of machine learning that we use everyday and perhaps have no idea that they are driven by ML. 1. Virtual Personal Assistants Siri, Alexa, Google Now are some of the popular examples of virtual personal assistants. As the name suggests, they assist in finding information, when asked over voice. All you need to do is activate them and ask “What is my schedule for today?”, “What are the flights from Germany to London”, or similar questions. For answering, your personal assistant looks out for the information, recalls your related queries, or send a command to other resources (like phone apps) to collect info. You can even instruct assistants for certain tasks l...
Post a Comment
Read more