Artificial Intelligence enables machines to think.
Machine Learning is a subset of Artificial Intelligence, It provides us with statistical tools to explore, analyze and understand the data, we have three different approaches in Machine Learning
1. Supervised learning –
We will have some labeled/parsed data, using this data we can do some predictions. E.g.: we have height and weight, we need to classify if person is obese or fit. We will create model and train the model as we have past data and we know what will be output of this particular data
2. Unsupervised learning :We don’t have labeled output , and will not know what is the output. we will solve clustering technique, based on some similarity of the data, it will group the data using Euclidean distance. The three popular clustering algorithm- kmeans, hierarchical clustering and dbscan clustering are used for unsupervised machine learning
3. Reinforcement learning/ Semi supervised
Some of part of the data will be labeled and latter on some part of the data will not be labeled , so the machine model learns slowly from past data and will learn after the new data will be coming up. Algorithm learns to react to the environment.
Deep learning, is a subset of Machine learning,
How it was created?
Scientist thought can we make machine learn like how we with help of human brain actually try to learn things, that is the main idea behind deep learning, In deep learning we create architecture called Multi neural network architecture
The different networks in deep learning
1. Artificial Neural Networks (ANN) – used where in most of problems statements, data are present in numbers
2. Convolution Neural Networks (CNN) – Input is in form of images , we will use in CNN
3. Recurrent Neural Networks (RNN) – Input is in form of time series , we will use in RNN
Using concepts of Machine learning and deep learning , we derive Artificial Intelligence application.E.g.:- self driving car , recommendation engine etc
Data science is technique that tries to applies all this particular parts and technique (Machine learning and deep learning )and uses some mathematical tool like statistics, probability, linear algebra , calculus etc