What is machine learning and its impact on our generation
what is machine learning ?
Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence.
Well this definition is little complex for someone like me , who has just started learning the concepts of machine learning so let us try to understand machine learning in more easy way.
What we can simply gather from the word Machine Learning is that Machine learns to do something. In traditional programming we provide our machine with input and a program and then the machine processes the data and produces output but, in case of machine learning we provide it with input and output and on basis of that machine learns the program to process the future input.
Whether we realize it or not we use machine learning in our day to day life be it Siri , Alexa ,Google assistant , auto tagging in Facebook ,google maps route predictions, face recognition and many more.
We all use Google assistant on our phones for different purposes. We use Google maps very frequently while we drive and if you notice it shows us the fastest route and approx. time to reach the destination and most of the time it is correct . In all these cases machine learning is used.
What made machine learning trending now
It is not that machine learning just made its way in computer science .It has existed for a long time but before it had some limitations but present developments have helped to increase use of machine learning . some of the factors which made machine learning possible are :
- MORE DATA AND CHEAPER STORAGE :
The rise of cloud based tools and the plummeting cost of storing data through services like amazon Red shift mean that more data than ever is generated and stored by business critical applications.
2.OPEN SOURCE LIBRARIES:
Widely available machine learning libraries like Google’s TensorFlow and Scikit-learn make cutting edge algorithms more accessible to a wider audience of data scientists and generalist software engineers.
3. GREATER HORSEPOWER:
The development of cloud based platforms and custom hardware optimized for machine learning means that these applications can run faster and at lower cost , increasing their suitability for variety of business needs.
Types of machine learning
There are so many different types of Machine Learning systems that it is useful to
classify them in broad categories based on:
• Whether or not they are trained with human supervision (supervised, unsupervised,Semi supervised, and Reinforcement Learning)
• Whether or not they can learn incrementally on the fly (online versus batch learning)
• Whether they work by simply comparing new data points to known data points, or instead detect patterns in the training data and build a predictive model, much like scientists do (instance-based versus model-based learning)
Machine Learning systems can be classified according to the amount and type of supervision they get during training. There are three major categories: supervised learning, unsupervised learning, and Reinforcement Learning.
Supervised learning
In supervised learning, the training data you feed to the algorithm includes the desired Solutions called labels.
In this case we have labeled and are trying to predict a label based off of known features.
A typical supervised learning task is classification. The spam filter is a good example Of this: it is trained with many example emails along with their class (spam or not a spam),and it must learn how to classify new emails.
Another typical task is to predict a target numeric value, such as the price of a car, given a set of features (mileage, age, brand, etc.) called predictors. This sort of task is called regression . To train the system, you need to give it many examples of cars, including both their predictors and their labels (i.e., their prices).
Unsupervised learning
Unsupervised learning is the training of an artificial intelligence (AI) algorithm using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance.
In this case we have unlabeled data and are trying to group together similar data points based off of features.
Reinforcement Learning
Reinforcement learning is an area of Machine Learning. Reinforcement. It is about taking suitable action to maximize reward in a particular situation. It is employed by various software and machines to find the best possible behavior or path it should take in a specific situation.
In this case the algorithm learns to perform an action from experience.
How it works
It works by creating an algorithm which a computer then uses to find a model that fits the data as best as possible , and makes very accurate predictions based on that.
A machine learning algorithm is a trial and error process and each consecutive trial is at least as the previous one. While training the the model we don’t provide it with a set of rules instead we provide it with the final goal which the model has to achieve . This is one of the many ways machine learning works and the process is what makes it special that we don’t have to program the model for every step it has to take rather the machine learns on its own about what steps it needs to take to achieve the final goal.
So how do we train the model , it is done by providing it with sufficient amount of training data on the basis of which it trains . once the model is trained it can be tested for different sets of data .
Real life applications of Machine Learning
1. IMAGE RECOGNITION
Image recognition is one of the most common uses of machine learning. There are many situations where you can classify the object as a digital image. Machine learning can be used for face detection in an image as well. There is a separate category for each person in a database of several people. Machine learning is also used for character recognition to discern handwritten as well as printed letters. We can segment a piece of writing into smaller images, each containing a single character.
2. MEDICAL DIAGNOSIS
Machine learning can be used in the techniques and tools that can help in the diagnosis of diseases. It is used for the analysis of the clinical parameters and their combination for the prognosis example prediction of disease progression for the extraction of medical knowledge for the outcome research, for therapy planning and patient monitoring. These are the successful implementations of the machine learning methods. It can help in the integration of computer-based systems in the healthcare sector.
3. FRIEND SUGGESTION AND AUTO TAGGING IN FACEBOOK
Facebook is the most widely used social media. Did you know that Facebook uses Machine Learning in almost every aspect? Whether your friend recommendations or auto-tagging of your friends in pictures Facebook uses Machine Learning.
4. SELF DRIVING CARS
We all have heard about the Tesla self driving cars project .This project uses machine learning to train the cars to drive safely on the roads.
All the vehicles Tesla have ever sold were built with the potential to one day become self-driving, although this fact was not made public until 2014 when a free upgrade was rolled out.
Tesla effectively crowd sources its data from all of its vehicles as well as their drivers, with internal as well as external sensors which can pick up information about a driver’s hand placement on the instruments and how they are operating them. As well as helping Tesla to refine its systems, this data holds tremendous value in its own right . Tesla uses this data to train the model for better results.
5. RECOMMENDATION SYSTEM
Have you ever wondered how amazon suggests you products to buy and how Netflix recommends you movies , both these functions uses machine learning .They rely on the data of users collected and use them to predict products and movies we would like.
These are few applications of Machine Learning but they are not limited to these examples . The applications of Machine Learning are limitless and in future it will further grow more ………
Conclusion
Machine Learning has changed the way we approach a problem and with increasing amount of different types of data which we collect throughout the world it holds an ocean of opportunities.
