Artificial Intelligence Vs Machine Learning Vs Deep Learning

Artificial intelligence is a branch of computer science which is all about making machines smart and intelligent.

Ex: Autonomous Vehicles, Google Assistant, Robots etc.

Machine Learning is technique used to implement Artificial Intelligence that can learn from data themselves without being Explicitly programmed.

Ex: Image Classification, Linear Regression models, price prediction etc.

Deep learning is a subset of Machine Learning which uses Artificial Neural Networks to learn from the data and gives the output.

Ex: Prediction of Diabetic Retinopathy, Cancer detection using X-Rays etc.

AI vs MLvs DL

Types of Machine Learning:

1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning

A) Supervised Learning: Supervised learning is all about the labelled data. We label or specify the features of objects, which means supervision. The labelled data are given to ML Model and when we give an unknown image as input, it tells what is the image all about.

Types of Supervised Learning:

1. Classification: Classification is about predicting the class label/categories for the new data, i.e. Finding the discrete values.
2. Regression: Regression is about predicting a continuous variable based on one or more independent variables.

Algorithms used in the Classification model:

1. Decision Tree Classification
2. Random Forest Classification
3. K-Nearest Neighbour

Algorithms used in the Regression model:

1. Logistic Regression
2. Polynomial Regression
3. Support Vector Machines

B) Unsupervised Learning: Unsupervised Learning is all about the unlabelled data. We give a bunch of random images and the ML model classifies into groups with respect to its features. It finds the patterns in the input data and classifies it into groups.

Types of Unsupervised Learning:

1. Clustering: This involves automatically grouping of data into clusters with respect to the input data.
2. Association: Association is a technique that checks for the dependency of one data item on another data item and maps accordingly so that it can be more profitable. It tries to find some interesting relations or associations among the variables in the dataset.

The Algorithms used in Unsupervised Machine Learning are:

1. K-Means Clustering
2. Hierarchical Clustering
3. Principal Component Analysis (PCA)
4. Apriori
5. Eclat

Supervised Learning Vs Unsupervised Learning

Deep Learning: Deep Learning is a subset of Machine learning which used Artificial Neural Networks to learn from the data. It mimics the action of Neurons in our brains. Deep learning is an AI function that mimics the workings of the human brain in processing data for use in detecting objects, recognizing speech, translating languages, and making decisions.

1. Deep learning can be Supervised, Unsupervised, Semisupervised.
2. Feature Extraction is not given in Deep Learning like the ML models
3. The mathematical model has Input layer, Several Hidden layers, Output layer.
4. The adjective deep refers to the use of multiple layers in the network.