Machine learning is a subset of artificial intelligence (AI) in which based on algorithms learn from historical data to predict outcomes and uncover patterns not easily spotted by humans. Machine learning algorithm learns by historical data , and deal with learning algorithms to uncover insights, decisions making , and make predictions about future trends. ML is now used in fraud detection, Market Price Prediction, Election exist-poll, Share Market etc.
1) Supervised Learning : As per name indicate , we train to machine by input data which is preclassified and labeled data that means some data is already define correct value. The goal of algorithm is refine set of classified and define input data and provide desired output based on applied rules to predict future trends with input data alone.
2) Unsupervised Learning : As per name indicate , We provide unsorted or no labels a and unclassified data are given to learning algorithm, leaving it discover structured and hidden patterns of inputs on its own. It have less focus on output more focus on exploring input data hidden patterns and structure.
3) Semi-supervised Learning : As per name indicate , We provide both kind of data labeled and unlabeled data for train to machine for improve the accuracy in result.
4) Reinforcement Learning: In this type of learning , We train to machine by feedback system, not in input data. Algorithm is learn form feedback and build most efficient path toward the goal.
Deep learning is a subset of machine learning in artificial intelligence (AI) . Deep learning algorithms run data through several “layers” of neural network algorithms, each of which passes a simplified representation of the data to the next layer. Deep learning is often made possible by artificial neural networks, which imitate neurons, or brain cells.
Artificial neural networks were inspired by things we find in our own biology. The neural net models use math and computer science principles to mimic the processes of the human brain, allowing for more general learning. An artificial neural network tries to simulate the processes of densely interconnected brain cells, but instead of being built from biology, these neurons, or nodes, are built from code.
All three of these AI concepts – machine learning, deep learning, and neural networks – can enable hardware and software robots to “think” and act dynamically, outside the confines of code.
