Machine learning(ML)

 Machine Learning:                                        

                                                Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, agriculture, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks. A subset of machine learning is closely related to computational statistics, which focuses on making predictions using computers, but not all machine learning is statistical learning. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a related field of study, focusing on exploratory data analysis through unsupervised learning.[Some implementations of machine learning use data and neural networks in a way that mimics the working of a biological brain.[In its application across business problems, machine learning is also referred to as predictive analytics.

                                                     

                                                  


Types of Machine Learning:

  • Supervised Learning
  • Unsupervised Learning
  • Reinforcement Learning

Supervised learning (SL): Supervised learning is a machine learning paradigm for problems where the available data consists of labelled examples, meaning that each data point contains features (covariates) and an associated label. The goal of supervised learning algorithms is learning a function that maps feature vectors (inputs) to labels (output), based on example input-output pairs. It infers a function from labelled training consisting of a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (also called the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. An optimal scenario will allow for the algorithm to correctly determine the class labels for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way . This statistical quality of an algorithm is measured through the so-called generalization error.

                


Unsupervised learning : Unsupervised learning is a type of algorithm that learns patterns from untagged data. The hope is that through mimicry, which is an important mode of learning in people, the machine is forced to build a concise representation of its world and then generate imaginative content from it.

In contrast to supervised learning where data is tagged by an expert, e.g. tagged as a "ball" or "fish", unsupervised methods exhibit self-organization that captures patterns as probability densities [1] or a combination of neural feature preferences encoded in the machine's weights and activations. The other levels in the supervision spectrum are reinforcement learning where the machine is given only a numerical performance score as guidance, and semi-supervised learning where a small portion of the data is tagged.


                                                                                                


Reinforcement learning (RL) : Reinforcement learning is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning.

Reinforcement learning differs from supervised learning in not needing labelled input/output pairs be presented, and in not needing sub-optimal actions to be explicitly corrected. Instead the focus is on finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge).

The environment is typically stated in the form of a Markov decision process (MDP), because many reinforcement learning algorithms for this context use dynamic programming techniques. The main difference between the classical dynamic programming methods and reinforcement learning algorithms is that the latter do not assume knowledge of an exact mathematical model of the MDP and they target large MDPs where exact methods become infeasible.



Comments

Post a Comment

Popular posts from this blog

Deep Learning

Image
  Deep Learning in AI Deep learning is based on the branch of machine learning, which is a subset of artificial intelligence. Since neural networks imitate the human brain and so deep learning will do. In deep learning, nothing is programmed explicitly. Basically, it is a machine learning class that makes use of numerous nonlinear processing units so as to perform feature extraction as well as transformation. The output from each preceding layer is taken as input by each one of the successive layers. Deep learning models are capable enough to focus on the accurate features themselves by requiring a little guidance from the programmer and are very helpful in solving out the problem of dimensionality. Deep learning algorithms a re used, especially when we have a huge no of inputs and in the deep learning has been evolved by the machine learning  which itself is a subset of artificial intelligence and as the idea behind the  artificial intelligence  is to mimi...
Read more

Expert Systems in AI

Image
  What is an Expert System? An expert system is a computer program that is designed to solve complex problems and to provide decision-making ability like a human expert. It performs this by extracting knowledge from its knowledge base using the reasoning and inference rules according to the user queries. The expert system is a part of AI, and the first ES was developed in the year 1970, which was the first successful approach of artificial intelligence. It solves the most complex issue as an expert by extracting the knowledge stored in its knowledge base. The system helps in decision making for complex problems using  both facts and heuristics like a human expert . It is called so because it contains the expert knowledge of a specific domain and can solve any complex problem of that particular domain. These systems are designed for a specific domain, such as  medicine, science,  etc. The performance of an expert system is based on the expert's knowledge stored in its...
Read more

Decision Management in AI

What is AI decision making? AI and decision management systems can help companies in making valid decisions by providing up-to-date and relevant information and performing analytic functions. Companies base their decisions on data available from management information systems as they reflect information that comes from the operations of their company. Combining AI and decision management systems can take decision-making to different levels. AI’s capabilities help these decision management systems in translating customer data into predictive models of key trends. This has helped marketing and consumer departments in customizing their efforts according to key demographics. AI AND DECISION MANAGEMENT: BENEFITS  Since its beginning, AI has played a revolutionary role in automating both knowledge based and non-knowledge based activities. Today, a huge amount of data is used for generating various models on a weekly basis or even on a daily basis, that help an organization in making deci...
Read more