Table of Contents
What is Artificial Intelligence?
Artificial intelligence is a vast field consisting of tool required to make computers behave intelligently.
What is Machine Learning?
Its a set of tools for making inferences(Cause for behaviour) and predicting from data. It’s an interdisciplinary field of Statistics and Computer Science which allows machines to learn to make a decision from data without explicitly programming it.
Machine learning algorithms build a mathematical model based on sample data, known as “training data”, in order to make predictions or decisions.
Often people get confused between AI, Machine learning and Data Science. But its really simple. AI is all about making computers smart and Machine learning is a subset of it. On the other side, Data Science is all about making sense from data and getting insights from it. Machine Learning/AI often used Data science to analyze data for making machines smarter and predicting by analyzing data.
Machine Learning Model?
The machine learning model is a statistical representation of a real-world processed on data.
Machine Learning Classification
Machine learning can be categorized into four main categories as shown in the below diagram.
1. Supervised Learning
Supervised learning is a learning in which we teach or train the machine using data which is well labeled that means some data is already tagged with the correct answer. After that, the machine is provided with a new set of examples(data) so that supervised learning algorithm analyses the training data(set of training examples) and produces a correct outcome from labelled data.
Predictor variables/features and a target variable and Aim is to predict the target variable, given the predictor values. Supervised learning is when the model is getting trained on a labelled dataset. The labelled dataset is one which has both input and output parameters. In this type of learning both training and validation, datasets are labelled as shown in the figures below.
It can be further categorized into two types as:
It has two main types: 1. Classification 2. Regression
- Classification: Classification is a process of categorizing a given set of data into classes, It can be performed on both structured or unstructured data. The process starts with predicting the class of given data points. The classes are often referred to as target, label or categories.
- Regression: A regression problem is when the output variable is a real or continuous value, such as “salary” or “weight”.
Unsupervised learning means no target column so it looks and analyze all data and tries to find patterns.
Unsupervised learning is the training of machine using information that is neither classified nor labelled and allowing the algorithm to act on that information without guidance. Here the task of machine is to group unsorted information according to similarities, patterns and differences without any prior training of data. Unlike supervised learning, no teacher is provided that means no training will be given to the machine. Therefore the machine is restricted to find the hidden structure in unlabeled data by our-self.
It can be used for problems like classifications/clusterization etc. In the case of unsupervised learning data we get is not labelled and the algorithm needs to find its own pattern in data. Sometimes when we get data in real life it does not contain label data as it can be too much manual data or labelling that data does not make any sense. For example, we have road data available for smart cars, it would be difficult to do labelling to that data.
One good example of unsupervised learning can is analyzing data and then categorizing patients in different groups.
Generative AI is one of the biggest recent advancements in artificial intelligence technology because of its ability to create something new. It opens the door to an entire world of possibilities for human and computer creativity, with practical applications emerging across industries, from turning sketches into images for accelerated product development, to improving computer-aided design of complex objects. It takes two neural networks against each other to produce new and original digital works based on sample inputs.
Supervised vs unsupervised Learning Data is generally labelled in supervised learning. On the other side in unsupervised learning data has only features and not labelled data.
2. Reinforcement Learning
Reinforcement learning is used for sequential actions. Example: A checker game-deciding its next move in the game. It is not common as Supervised and Unsupervised learning and uses complex mathematics like game theory for applications.