History of Machine Learning
The term machine learning was first introduced by Arthur Samuel in 1959. He was an American pioneer in the field of computer gaming and artificial intelligence.
Definition of Machine Learning
Machine Learning is said as a subset of artificial intelligence that is mainly concerned with the development of algorithms which allow a computer to learn from the data and past experiences on their own.
So the next questions raises that,
Q1) How do machines learn?
-> Well the answer is from the Training Data. Data scientists uses data to train machine learning models that can make predictions based on the relationships they find in the data.
Q2) How does Machine Learning work ?
-> Before we dive down into how it’s work we have to understand about Machine learning models.
Machine learning models
A Machine Learning system learns from trained data using algorithm, and whenever it receives new data, predicts the output for it.
Training Data is a sample of historical data. From the text messages, emails, and social media posts we send to the photographs and videos we take on our phones, we generate massive amounts of information. More data still is created by millions of sensors in our homes, cars, cities, public transport infrastructure, and factories. Training data is further divided into labeled data and Unlabeled data. The accuracy of predicted output depends upon the amount of data, as the huge amount of data helps to build a better model which predicts the output more accurately.
Algorithm used finds relationships between the features of the samples (Input data) and the labeled/training data. Less the time complexity in algorithm, faster the output will be.
Working of Machine learning with example?
Suppose volunteers want to identify different breed of dogs using a phone app.
- A team of dog specialists and data scientists collects photo of different breed of dogs.
- The team labels the samples with the correct breed.
- The labeled data is processed using an algorithm that finds relationships between the features of the samples and the labeled breed.
- The results of the algorithm are encapsulated in a model.
- When new samples are found by volunteers, the model can identify the correct breed label.
Labeled and Unlabeled Data
Unlabeled data — Data which consists of samples of natural or human-created artifacts that you can obtain relatively easily from the world. Some examples of unlabeled data might include photos, audio recordings, videos, news articles, tweets, etc. It just contains the data, and no meaningful “tag,” “label,” or “class” are here.
Labeled data — It takes a set of unlabeled data and put with some sort of meaningful “tag,” “label,” or “class” that is somehow informative or desirable to know.
Type of Machine Learning
3 type of machine learning –
- Supervised learning
- Unsupervised learning
- Reinforcement learning
Supervised learning — This type of learning uses labelled training data.
Unsupervised learning — This type is used where data is unlabeled.
Reinforcement learning — Used where some data are labeled and some are data unlabeled.