Machine learning
According to Alp Aydin (2010), Machine learning is an area of artificial intelligence that developed from design acknowledgment and computational learning hypothesis. It investigates the study and development of calculations that can gain from and make expectations on information. Such calculations work by building a model from sample inputs keeping in mind the end goal to settle on information driven forecasts or choices, as opposed to taking after entirely static project guidelines.
Machine learning is firmly identified with computational statistics; a specialty that goes for the configuration of calculation for executing factual techniques on computers. It has solid ties to numerical enhancement, which conveys techniques, hypothesis and application areas to the field. Machine learning is utilized in a scope of registering errands where outlining and programming unequivocal calculations is in feasible (Marshland, 2009). Concepts of machine learning
1. Bayesian networks
A Bayesian network is a probabilistic graphical model that speaks to an arrangement of irregular variables and their restrictive independencies through a coordinated non-cyclic chart. For instance, a Bayesian system could speak to the probabilistic connections between forex market and political unrests. Given the instances of political unrests, the system can be utilized to figure the probabilities of the forex market dropping. Proficient calculations exist that perform surmising and learning.

2. Decision tree learning
It uses a decision tree as a predictive model, which maps observations about an item to conclusions about the item's target value.
3. Association rule learning
It is a method for discovering interesting relations between variables in large databases.
4. Artificial neural networks
It is a learning algorithm inspired by structure and functional characteristics of biological neural networks.
Calculations are organized as far as an interconnected gathering of fake neurons, preparing data utilizing a linking way to deal with calculation. Current neural systems are nonlinear measurable information demonstrating devices. They are normally used to model complex connections in the middle of inputs and yields, to discover instances in information, or to congregate the measurable structure in an obscure joint likelihood conveyance between observed variables
5. Clustering
Cluster analysis is the assignment of a set of observations into subsets so that observations within the same cluster are similar according to some pre designated criterion or criteria, while observations drawn from different clusters are dissimilar.
6. Support vector machines
It is an arrangement of related directed learning routines utilized for order and relapse. Given an arrangement of preparing illustrations, each checked as fitting in with one of two classifications, a support vector machine formulating algorithm assembles a model that predicts whether another case falls into one class or the other.

Current trends in machine learning
1. Deep Learning
Deep learning is the automatic construction of deep models from data. They are called “deep” because the models compute desired functions in multiple steps, rather than trying to solve problems in one or two steps. Deep learning is typically accomplished using neural networks, which are models that use matrix multiplication and non-linearity to build their functions.
2. Large-Scale Training
Large-scale training has continued to be an interesting research vein. While not that many people have training sets above 1TB, the models that use that scale data tend to be commercially very valuable. Training in machine learning is a form of parameter optimization: a machine learning model can be viewed as having a set of knobs that are adjusted to make the model perform well on a training set. Large-scale training then becomes large-scale optimization.
3. Latent Structured Active Learning
It combines structured prediction problems with active learning. It uses weakly supervised learning. Its application is to predict the 3D layout of rooms from single images.

4. Automatic Construction and Natural-Language Description of Nonparametric Regression Models
It is a non-parametric formulation of functions that model high-level properties, e.g. smoothness. It is a compositional structure of the “language of models” which results in an automated way to describe data.

Applications of machine learning
1. Automating employee access control
It involves develop a computer algorithm that will predict which employees should be granted access to what resources. These auto-access models seek to minimize the human involvement required to grant or revoke employee access.
2. Search engines
Search engines use machine learning to anticipate user demands. They learn user browsing patterns and later provide the user with information relevant to user search history and hence the user can access information needed easily.
3. Stock market analysis
The stock market has been using machine learning for a long time to analyse numerous volumes of data. Machine learning enables prediction to be made in either the increase or decline of the market prices to enable investors make smart choices when investing in the stock market.
4. Medical diagnosis
Machine learning is used to make medical diagnosis based on system being equipped information on symptoms of diseases. The systems can then know what disease a patient is suffering from the symptoms that he or she has.
5. Software engineering
Software engineering uses machine learning to enable developers come with systems at a fast pace. It also enhances development by presenting developers with current information on the software they intend to produce.
6. Advertising on web pages
Advertising on web pages has increased rapidly in recent years as more and more people get access to internet. Users get presented with other related products if they access a page with certain products. This is done through machine learning. References

1. Sra, S., Nowozin, S., & Wright, S. J. (2012). Optimization for machine learning. Cambridge, Mass: MIT Press.
2. Alp Aydin, E. (2010). Introduction to machine learning. Cambridge, Mass: MIT Press.
3. Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2012). Foundations of machine learning. Cambridge, MA: MIT Press
4. Murphy, K. P. (2012). Machine learning: A probabilistic perspective. Cambridge, Mass: MIT Press.
5. Marshland, S. (2009). Machine learning: An algorithmic perspective. Boca Raton: CRC Press.