Machine Learning
Machine Learning
Machine learning (ML) is the study of computer algorithms. It is a subset of artificial intelligence. To make predictions and decisions, machine learning algorithms build a mathematical model based on sample data, known as "training data". Machine learning focuses on making predictions using computers, so it is closely related to computational statistics. Machine learning algorithms are used in a wide variety of applications, such as email filtering, computer vision, etc. It involves computers discovering how they can perform tasks without being explicitly programmed. It also involves computers learning from data provided so that they carry out certain tasks. The discipline of machine learning employs various approaches to teach computers to accomplish tasks where no fully satisfactory algorithm is available.
CATEGORIES
Machine learning approaches are traditionally divided into three broad categories, depending on the nature of the "signal" or "feedback" available to the learning system. They are
Supervised learning: Supervised learning algorithms build a mathematical model of a set of data that contains both the inputs and the desired outputs. The data is known as training data and consists of a set of training examples. Each training example has one or more inputs and the desired output, also known as a supervisory signal.
Unsupervised learning: Unsupervised learning algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points. The algorithms, therefore, learn from test data that has not been labeled, classified, or categorized. Instead of responding to feedback, unsupervised learning algorithms identify commonalities in the data and react based on the presence or absence of such commonalities in each new piece of data. A central application of unsupervised learning is in the field of density estimation in statistics, such as finding the probability density function.
Reinforcement learning: Reinforcement learning is an area of machine learning concerned with how software agents ought to take actions in an environment to maximize some notion of cumulative reward. Due to its generality, the field is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics, and genetic algorithms.
Other approaches are also being developed but they don’t fit neatly into this three-fold categorization.
The term machine learning was coined in 1959 by Arthur Samuel, an American IBMer, and pioneer in the field of computer gaming and artificial intelligence. Machine learning grew out of the quest for artificial intelligence. In the early day of AI, some researchers were interested in having machines learn the data. They attempted to approach the problem with various symbolic methods, known as “neural networks”. It started to flourish in the years of 1990s, recognized as a separate field. It shifted focus towards the methods and models borrowed from statistics and probability theory from AI. Soon, tackling solvable problems of a practical nature became its goal. Machine learning and data mining often employ the same methods and overlap significantly, but while machine learning focuses on prediction, based on known properties learned from the training data, data mining focuses on the discovery of unknown properties in the data. It also has intimate ties to optimization. Statistics is also considered as a closely related field to machine learning in terms of methods. But they are different in their principle goal.
LIMITATIONS
There are many approaches to machine learning. Some of them are agriculture, anatomy, bioinformatics, affective computing, machine translation, etc. Machine learning programs often fail to deliver expected results. There are many reasons for these limitations
Lack of (suitable) data
Lack of access to the data
Data bias
Privacy problems
Badly chosen tasks and algorithms
Wrong tools and people
Lack of resources
Evaluation problems
In particular, machine learning approaches can suffer from different databases. A machine learning system trained on current customers only may not be able to predict the needs of new customer groups that are not represented in the training data. When trained on man-made data, machine learning is likely to pick up the same constitutional and unconscious biases already present in society. Machine learning systems used for criminal risk assessment are biased against black people.
ML is a powerful tool we are only just beginning to understand and that is a profound responsibility. Since the 2010s, advances in both machine learning algorithms and computer hardware have led to more efficient methods for training deep neural networks (a particular narrow subdomain of machine learning) that contain many layers of non-linear hidden units. Software suites containing a variety of machine learning algorithms. Machine learning poses a host of ethical questions. Systems that are trained on datasets collected with biases may exhibit these biases upon use, thus digitizing cultural prejudices. Machines trained in language corpora will necessarily also learn these biases Because human languages contain biases. Till now machine learning has not developed to its full potential. So, in the future, we will be able to see a broad and advanced structure of the machine learning system.
Comments
Post a Comment