Machine Learning

What is machine learning

Machine is a mechanical structure that uses power to apply forces and control movement to person an intend action. its a thing that is created by a people to make work easier . Machine learning is a branch of artificial intelligence that deals with the design and development of algorithms. Compared to human beings machine learning is still very localized and nascent to the problem for which it is designed 

Machine learning is about creating a model that closely represent that part of the real world which is captured in the training data.Machine learning consist of mathematical formula,decision criteria and multidimensional parameters.we can say machine learning and Artificial intelligence are close to each other. 

We love bringing the latest and greatest machine learning techniques, breakthroughs, and developments to you in the form of articles and blogs.

The basic of machine learning

We know human learn from their past experiences and the machine follow instruction given by human.

Every machine learning algorithm has three component : 

Representation : how to represent knowledge . Examples include decision trees , set of rule , instance, 

graphical model, model ensembles and others evaluation : the way to evaluate candidate programs . 

Data and output is run on the computer to create a program. machine learning is like farming or gardening seed is the algorithms nutrients is data , the Gardner is you and plants is the programs.

Application of machine learning 

Machine learning is an application of artificial intelligence that prove system the ability to automatically learn and improve from experience without being explicitly program. 

Machine learning focus on the development of computer program that can access data and use it learn for themselves. 

In our daily life we also use machine learning for example spamming is one of them .

Recently if you saw the googles new product you can open up just your camera app and you can see the restaurants name and can see the restaurants name and based on hand writing prediction , image prediction and logo prediction it can query to the huge amount of data set that present at the google and can find out the rating of the restaurants, name of the restaurants and some reviews about the restaurants. 

Another example is, have you use some kind of app which predicts how will you look like on your 80 age or on your 90 age,how Your scene is going to get some kind of deformation . These are happen due to machine learning. 

 

Few example of machine learning:- There are many example we use in our everyday and perhaps have no idea that they are driven by machine learning.

• Virtual personal assistants
• Prediction while community
• Video surveillance
• Social media service
• Email spam
• Search engine result refining

Why we use machine learning

Machine learning is one modern innovation that has helped man enhance not only man . 

It help in multiple field industry, and professional process for example medical diagnosis , image processing, prediction, classification , learning association , extraction , regression, financial service , speech recognition , statistical arbitrage. it also advantages everyday living .

 Machine learning is helping in creating better technology to power today's ideas. 

We define machine learning as a set of method that can automatically detect patterns in data,and then use the uncovered patterns to predict future data or to perform other kinds of decision making under uncertainty(such as collect more data).

Types of machine learning

Machine learning is of following type

• Supervised learning
• Unsupervised learning
• Reinforcement learning
• Deep learning
• Deep reinforcement learning

Supervised learning

The name supervised learning is originates from the idea that training this type of algorithm is like a teacher having a supervise the whole process.

When training a supervised learning algorithm ,the training data will consist of inputs paired with the correct outputs. 

 It is also called as inductive learning, Training data include desired output . This is spam this is not. learning is supervised.

Reinforcement learning

Reinforcement learning is an intriguing and complex field.  Games! The term itself is enough to ignite the spark of enthusiasm inside us – there is nothing quite like it. There are certain concepts you should be aware of before wading into the depths of deep reinforcement learning A reinforcement learning task is about training an agent which interacts with its environment. The agent arrives at different scenarios known as states by performing actions. Actions lead to rewards which could be positive and negative. Machine learning is ubiquitous in the industry these days. 

In classification problems, we use two types of algorithms :

• class output
• probability output

Unsupervised learning

Training data does not include desired output . for example is clustering . it is hard to tell what is not.

Task that are too complex to program

• Task performed by animals or humans :

• Human beings perform routinely yet our introspection concerning how we do them is not sufficiently elaborate to extract a well defined program example of such task include driving,speech recognition, and image understanding.
• In all of these task set of the art machine learning programs , programs that learn from "that experience". Achieve quite satisfactory results,once exposed to sufficiently many training examples.



• Task beyond human capabilities:

• Another wide family of task that benefits from machine learning techniques are related to the analysis of very large and complex data sets these are Astronomical data,turning medical archives into medical knowledge,weather prediction,analysis of genomic data,web search engines and electronic commerce.

Computer vision

It  is revolutionizing sectors from agriculture to banking, from hospitality to security, and much more “Deep learning models required hours or days to train, especially on our local machines”.That’s a widespread belief among a lot of data science enthusiasts. 

We have heard this countless times from aspiring Data Scientists who shy away from building deep learning models on their own machines.

 Image segmentation creates a pixel-wise mask for each object in the image. We also discussed the two types of image segmentation: Semantic Segmentation and Instance Segmentation. 

 The possibilities of working with images using computer vision techniques are-endless. But I’ve Researched and got to know  a trend among data scientists recently.  A colored image is typically composed of multiple colors and almost all colors can be generated from three primary colors. The simplest way to create features from an image is to use these raw pixel values as separate features. I feel this is a very important part of a data scientist’s toolkit given the rapid rise in the number of images being generated these days. here they did not want to explain a multi image classification model. they only design their poster. they help us to guide make our own multi-label image.

Aim of machine learning

The purpose of machine learning is to discover better in your and then make prediction base on often complex patterns to answer business question , detect and analyse trends and help solve problem.

Domains of machine learning

Machine learning is perhaps the principal technology behind two emerging domains . 

Data science and artificial intelligence the rise of machine learning is coming about through the availability of data and computation , but machine learning methodologies are fundamentally depend on model.

Conclusion for machine learning

Machine learning is technique of training machines to perform the activities that a human brain can do , a bit faster and better than average Hunan being .

Today we have seen that the machine can beat human champions in game such as chess, Alpha Go , which are considered very complex .

You have seen that machines can be trained to perform human activities in several areas and can aid human in living better life . we have simple techniques in machine learning. 

There are more and more technique apply machine learning as a solution .

In the future machine learning will play an important role in our daily life. 

                                         

I am passionate about my work. Because  I love what  I do, I have a  steady source of  motivation that  drives me to do my best.  This    passion led me to  challenge myself  daily and learn new skills that  helped me to do better work.

                                                                                                       

Thank you for not only your good work but also for all the support you have given each other throughout the Blog, that's what makes the team stronger!