Hello everyone, this my first article on Medium. I am very happy to share my views on this thing. In this article, we will be discussing the most fundamental thing in Data Science like what is the difference between Artificial Intelligence Machine Learning, Deep Learning, and Data Science.
First of all, we talk about artificial intelligence. So, A.I. is a kind of application that will be able to perform some kind of task intelligently by itself. So, when you will be able to build some kind of product or kind of an application which will be able to give you a response, which will be able to do some prediction, forecasting out of some input, that is called A.I application. For example a self-driving car, recommendation system, chatbots, amazon shopping website, weather forecasting, etc. We always try to find out a relationship between the dataset in machine learning and deep learning.
So, when I talk about Machine Learning. It is a subset of A.I. It provides us the statistical tool to explore and understand the particular data. In machine learning, you have three different approaches –
1 Supervised machine learning
2 Unsupervised machine learning
3 Reinforcement machine learning
In the case of supervised learning, we will be having some labeled data and with the help of this kind of data, we will be actually able to do the prediction for the future. For example, Predicting House prices
First, we need data about the houses: square footage, number of rooms, features, whether a house has a garden or not, and so on. We then need to know the prices of these houses, i.e. the corresponding labels. By leveraging data coming from thousands of houses, their features, and prices, we can now train a supervised machine learning model to predict a new house’s price based on the examples observed by the model.
In the case of unsupervised learning, we will not be having labeled data. This means in my dataset I will not know what will is the output. In this, we usually solve the clustering type of problems. Clustering means based on the similarity of the data, it will try to group the data together. The most popular clustering algorithms are hierarchical clustering, k-means clustering, DB scan clustering.
In Reinforcement learning, some parts of your data will be labeled, and later on, some parts of the data will not be labeled. So by this kind of data model learn slowly by seeing the past data and it will be learning as soon as the new data will be coming up.
Deep learning is a subset of machine learning. In deep learning, we try to solve each and everything with the help of a Neural Network. The main idea behind the Neural Network is to mimic the human brain. We create architecture which is called a multi-layer neural network architecture.
In Deep learning, you have various techniques-
1 ANN- Artificial Neural Network
2 CNN- Convolution Neural Network
3 RNN- Recurrent Neural Network
Most of the data which is actually present in the form of numbers will be solved with the help of ANN.
If our data is in the form of images, then we will use CNN. CNN is especially prevalent in image and video processing projects.
And if our data is in the form of a time series kind of data, at that time we will use RNN. We can use recurrent neural networks to solve the problems related to:
- Time Series data
- Text data
- Audio data
Data Science is a technique that tries to apply Machine Learning and Deep Learning and it also uses some mathematical tools like statistics, probability, linear algebra, calculus.
A data scientist has to work on Machine Learning, Deep Learning based on the type of use case by using some mathematical tools. Some other tools which you will be required to work on end to end projects like –
1 Feature Engineering
2 Exploratory Data Analysis
3 Statistics and Probability
4 Data Extraction, Transformation, Loading
5 Linear Algebra and Calculus
6 Cloud Computing
7 Docker
8 Database Management