Let’s Understand The Basic Different in Artificial Intelligence, Machine Learning, Deep Learning and Data Science.
What is Artificial Intelligence?
1. The core purpose of AI is to impart human intelligence to machines.
2. It specifically focusses on making the devices more intelligent and thinks as well as act like humans.
Example are:
1. Self-driving cars
2. Robots are the best examples of AI.
What is Machine Learning?
1. ML is a subset of AI that exclusively focuses on making predictions based on buyer experiences.
2. It enables the computer to make a data-driven decision rather than explicitly program for carrying out a specific task.
3. ML devices are designed in a specific way that learns and improved over time and helps the user to make a better decision.
Types of machine learning
· Supervised learning
· Unsupervised learning
· Reinforcement learning
Machine Learning deals with the listed below issues:
· Analyze data
· Collect data
· Filter data
· Train algorithms
· Test algorithms
· Use algorithms for future predictions
Example of ML:
1. Image recognition
2. Improve search engine result
3. Personal assistant
a. Google Assistant
b. Amazon Alexa
c. Apple Siri
4. Redefined product recommendation
What is Deep Learning?
1. Computer software that mimics the network of neurons in a brain.
2. It is a subset of machine learning based on artificial neural network with representation learning.
3. It’s learning can be supervised or unsupervised learning.
Deep learning algorithms are constructed with connected layers:
1. Input Layer
2. Hidden Layer: All layers in between Input Layer and Output Layer are called Hidden Layers. The work deep means the network join neurons in more than two layers.
3. Output Layer
Deep Learning Process
Work Area of Deep Learning
1. Self-driving technology
2. Aerospace and Defence
3. Medical Research
4. Industry Automation
Deep Learning Example:
the model is trying to learn how to dance. After 10 minutes of training, the model does not know how to dance, and it looks like a scribble.
After 48 hours of learning, the computer masters the art of dancing.
Types of Deep Learning Networks
Disadvantages of deep learning
- It is very expensive, need commercial-grade GPUs.
What is Data Science?
1. Data science is a multidisciplinary term for a whole set of tools and techniques of data inference and algorithm development to solve complex analytical problems.
2. It is used in various fields such as machine learning, visualization, statistics more.
3. It’s a process as well as a method that analyze and manipulate the data.
4. It also enables us to find the meaning and appropriate information from the large volumes of data.
5. It makes it convenient to use data for making viable business decisions in science, business, technology as well as in politics.
The data science life cycle has six different phases:
1. Discovery
2. Data preparation
3. Model planning
4. Model building
5. Communicating results
6. Operationalizing
