Introduction to Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence
Artificial Intelligence (AI) means teaching computers to do smart things, like learning from experience, understanding language, and solving problems, just like people do.
Machine Learning(ML)
Machine learning is a subset of Artificial Intelligence and it is like teaching computers to learn from examples, so they can make decisions or predictions on their own. It’s about computers getting smarter by looking at data and figuring things out by themselves.
Importance of machine learning :
Machine learning is important because it helps computers learn and improve on their own without being told exactly what to do. It makes things personalized by giving recommendations based on what it learns from lots of information. Also, it helps find patterns to make processes work better and saves time and money. It leads to new inventions and better ways of doing things in different fields. Overall, machine learning is essential because it makes computers smarter and helps make life easier and more innovative.
Machine Learning Development Life Cycle(MLDLC) :
Types of Machine Learning :
Machine learning can be classified into 4 types of algorithms.
- Supervised Learning :-
Supervised Learning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs. It infers a function from labeled training data consisting of a set of training examples.
Supervised learning are of two types they are:
Classification :- They deal with discrete data
Regression :- They deal with continuous data
- Classification : It specifies the class to which data elements belong to and is best used when the output has finite and discrete values. It predicts a class for an input variable as well.
It is used in Spam detection, Churn prediction, Sentiment analysis,e.t.c…
2. Regression : It aims to model the relationship between a certain number of features and a continuous target variable.
It is used in Predicting stock prices and predicting prices of homes,e.t.c…
Supervised Machine learning Algorithms
- K-nearest Neighbors
- Linear Regression
- Support vector machines
- Decision tree
- Random forest
- Neural Networks
2. Unsupervised learning
Unsupervised learning is a type of machine learning that looks for previously undetected patterns in a data set with no pre-existing labels and with a minimum of human supervision.
It uses in identification of cancer cells and e.t.c….
3. Semi-supervised learning
Semi-supervised learning is an approach to machine learning that combines a small amount of labeled data with a large amount of unlabeled data during training. Semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data).
This model is used in complex medical research applications, speech analysis, and fraud detection and e.t.c…
4.Reinforcement learning
Reinforcement learning is like teaching a computer to learn from trial and error. The computer tries different actions in an environment and learns from the outcomes, getting rewards for good actions and penalties for bad ones. Over time, it figures out the best actions to take to maximize its rewards.
It can be used in video games, Robotics,Recommendation Systems and e.t.c…
Deep Learning
Deep learning is a type of machine learning where computers learn to recognize patterns in data by using networks that mimic the human brain’s structure. It’s really good at tasks like understanding images, language, and speech.