Definition

machine learning

Contributor(s): Ed Burns

Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.

Recommendation engines are a common use case for machine learning. Other popular uses include fraud detection, spam filtering, malware threat detection, business process automation (BPA) and predictive maintenance.

Types of machine learning

Classical machine learning is often categorized by how an algorithm learns to become more accurate in its predictions. There are four basic approaches: supervised learning, unsupervised learning, semi-supervised learning and reinforcement learning. The type of algorithm a data scientist chooses to use depends on what type of data they want to predict.

  • Supervised learning. In this type of machine learning, data scientists supply algorithms with labeled training data and define the variables they want the algorithm to assess for correlations. Both the input and the output of the algorithm is specified.
  • Unsupervised learning. This type of machine learning involves algorithms that train on unlabeled data. The algorithm scans through data sets looking for any meaningful connection. Both the data algorithms train on and the predictions or recommendations they output are predetermined.
  • Semi-supervised learning. This approach to machine learning involves a mix of the two preceding types. Data scientists may feed an algorithm mostly labeled training data, but the model is free to explore the data on its own and develop its own understanding of the data set.
  • Reinforcement learning. Reinforcement learning is typically used to teach a machine to complete a multi-step process for which there are clearly defined rules. Data scientists program an algorithm to complete a task and give it positive or negative cues as it works out how to complete a task. But for the most part, the algorithm decides on its own what steps to take along the way.

How supervised machine learning works

Supervised machine learning requires the data scientist to train the algorithm with both labeled inputs and desired outputs. Supervised learning algorithms are good for the following tasks:

  • Binary classification. Dividing data into two categories.
  • Multi-class classification. Choosing between more than two types of answers.
  • Regression modeling. Predicting continuous values.
  • Ensembling. Combining the predictions of multiple machine learning models to produce an accurate prediction.

How unsupervised machine learning works

Unsupervised machine learning algorithms do not require data to be labeled. They sift through unlabeled data to look for patterns that can be used to group data points into subsets. Most types of deep learning, including neural networks, are unsupervised algorithms. Unsupervised learning algorithms are good for the following tasks:

  • Clustering. Splitting the data set into groups based on similarity.
  • Anomaly detection. Identifying unusual data points in a data set.
  • Association mining. Identifying sets of items in a data set that frequently occur together.
  • Dimensionality Reduction. Reducing the number of variables in a data set.

How semi-supervised learning works

Semi-supervised learning works by data scientists feeding a small amount of labeled training data to an algorithm. From this, the algorithm learns the dimensions of the data set, which it can then apply to new, unlabeled data. The performance of algorithms typically improves when they train on labeled data sets. But labeling data can be time-consuming and expensive. Semi-supervised learning strikes a middle ground between the performance of supervised learning and the efficiency of unsupervised learning. Some areas where semi-supervised learning is used include:

  • Machine translation. Teaching algorithms to translate language based on less than a full dictionary of words.
  • Fraud detection. Identifying cases of fraud when you only have a few positive examples.
  • Labeling data. Algorithms trained on small data sets can learn to apply data labels to larger sets automatically.

How reinforcement learning works

Reinforcement learning works by programming an algorithm with a distinct goal and a prescribed set of rules for accomplishing that goal. Data scientists also program the algorithm to seek positive rewards -- which it receives when it performs an action that is beneficial toward the ultimate goal -- and avoid punishments -- which it receives when it performs an action that gets it farther away from its ultimate goal. Reinforcement learning is often used in areas like:

  • Robotics. Robots can learn to perform tasks in the physical world using this technique.
  • Video gameplay. Reinforcement learning has been used to teach bots to play a number of video games.
  • Resource management. Given finite resources and a defined goal, reinforcement learning can help enterprises plan how to allocate resources.
How machine learning works
Machine learning is like statistics on steroids.

Uses of machine learning

Today, machine learning is used in a wide range of applications. Perhaps one of the most well-known examples of machine learning in action is the recommendation engine that powers Facebook's News Feed.

Facebook uses machine learning to personalize how each member's feed is delivered. If a member frequently stops to read a particular group's posts, the recommendation engine will start to show more of that group's activity earlier in the feed.

Behind the scenes, the engine is attempting to reinforce known patterns in the member's online behavior. Should the member change patterns and fail to read posts from that group in the coming weeks, the News Feed will adjust accordingly.

In addition to recommendation engines, other uses for machine learning include the following:

Customer relationship management -- CRM software can use machine learning models to analyze email and prompt sales team members to respond to the most important messages first. More advanced systems can even recommend potentially effective responses.

Business intelligence -- BI and analytics vendors use machine learning in their software to identify potentially important data points, patterns of data points and anomalies.

Human resource information systems -- HRIS systems can use machine learning models to filter through applications and identify the best candidates for an open position.

Self-driving cars -- Machine learning algorithms can even make it possible for a semi-autonomous car to recognize a partially visible object and alert the driver.

Virtual assistants -- Smart assistants typically combine supervised and unsupervised machine learning models to interpret natural speech and supply context.

Advantages and disadvantages

Machine learning has seen powerful use cases ranging from predicting customer behavior constituting the operating system for self-driving cars. But just because some industries have seen benefits doesn't mean machine learning is without its downsides.

When it comes to advantages, machine learning can help enterprises understand their customers at a deeper level. By collecting customer data and correlating it with behaviors over time, machine learning algorithms can learn associations and help teams tailor product development and marketing initiatives to customer demand.

Some internet companies use machine learning as a primary driver in their business models. Uber, for example, uses algorithms to match drivers with riders. Google uses machine learning to surface the right advertisements in searches.

But machine learning comes with disadvantages. First and foremost, it can be expensive. Machine learning projects are typically driven by data scientists, who command high salaries. These projects also require software infrastructure that can be high-cost.

There is also the problem of machine learning bias. Algorithms that trained on data sets that exclude certain populations or contain errors can lead to inaccurate models of the world that, at best, fail and, at worst, are discriminatory. When an enterprise bases core business processes on biased models, it can run into regulatory and reputational harm.

Choosing the right machine learning model

The process of choosing the right machine learning model to solve a problem can be time-consuming if not approached strategically.  

Step 1: Align the problem with potential data inputs that should be considered for the solution. This step requires help from data scientists and experts who have a deep understanding of the problem.

Step 2: Collect data, format it and label the data if necessary. This step is typically led by data scientists, with help from data wranglers.

Step 3: Chose which algorithm(s) to use and test to see how well they perform. This step is usually carried out by data scientists.

Step 4:  Continue to fine-tune outputs until they reach an acceptable level of accuracy. This step is usually carried out by data scientists with feedback from experts who have a deep understanding of the problem.

Importance of human-interpretable machine learning

Explaining how a specific ML model works can be challenging when the model is complex. There are some vertical industries where data scientists have to use simple machine learning models because it's important for the business to explain how each and every decision was made. This is especially true in industries with heavy compliance burdens like banking and insurance.

Complex models can accurate predictions, but explaining to a layperson how an output was determined can be difficult. 

The future of machine learning

While machine learning algorithms have been around for decades, they've attained new popularity as artificial intelligence (AI) has grown in prominence. Deep learning models, in particular, power today's most advanced AI applications.

Machine learning platforms are among enterprise technology's most competitive realms, with most major vendors, including Amazon, Google, Microsoft, IBM and others, racing to sign customers up for platform services that cover the spectrum of machine learning activities, including data collection, data preparation, data classification, model building, training and application deployment.

As machine learning continues to increase in importance to business operations and AI becomes ever more practical in enterprise settings, the machine learning platform wars will only intensify.

How deep learning differs from traditional machine learning
Deep learning works in very different ways from traditional machine learning.

Continued research into deep learning and AI is increasingly focused on developing more general applications. Today's AI models require extensive training in order to produce an algorithm that is highly optimized to perform one task. But some researchers are exploring ways to make models more flexible and are seeking techniques that allow a machine to apply context learned from one task to future, different tasks.

History of machine learning

1642 - Blaise Pascal invents a mechanical machine that can add, subtract, multiply and divide.

1679 - Gottfried Wilhelm Leibniz devises the system of binary code.

1834 - Charles Babbage conceives the idea for a general all-purpose device that could be programmed with punched cards.

1842 - Ada Lovelace describes a sequence of operations for solving mathematical problems using Charles Babbage's theoretical punch-card machine and becomes the first programmer.

1847 - George Boole creates Boolean logic, a form of algebra in which all values can be reduced to the binary values of true or false.

1936 - English logician and cryptanalyst Alan Turing proposes a universal machine that could decipher and execute a set of instructions. His published proof is considered the basis of computer science.

1952 - Arthur Samuel creates a program to help an IBM computer get better at checkers the more it plays.

1959 - MADALINE becomes the first artificial neural network applied to a real-world problem: removing echoes from phone lines.

1985 - Terry Sejnowski and Charles Rosenberg's artificial neural network taught itself how to correctly pronounce 20,000 words in one week.

1997 - IBM's Deep Blue beat chess grandmaster Garry Kasparov.

1999 - A CAD prototype intelligent workstation reviewed 22,000 mammograms and detected cancer 52% more accurately than radiologists did.

2006 - Computer scientist Geoffrey Hinton invents the term deep learning to describe neural net research.

2012 - An unsupervised neural network created by Google learned to recognize cats in YouTube videos with 74.8% accuracy.

2014 - A chatbot passes the Turing Test by convincing 33% of human judges that it was a Ukrainian teen named Eugene Goostman.

2014 - Google's AlphaGo defeats the human champion in Go, the most difficult board game in the world.

2016 - LipNet, DeepMind's artificial-intelligence system, identifies lip-read words in video with an accuracy of 93.4%.

2019 - Amazon controls 70% of the market share for virtual assistants in the U.S.

This was last updated in June 2020

Next Steps

Why machine learning models require a failover plan

Explore common machine learning use cases in IT operations

Continue Reading About machine learning

Dig Deeper on Machine learning platforms

Join the conversation

15 comments

Send me notifications when other members comment.

Please create a username to comment.

How does your enterprise plan to implement machine learning?
Cancel
How the machine learning will affect the QA people ?
Cancel
But, isn't it programmed to do so...its just that It will behave in the same manner for different set of users and their friends.
Cancel
Machine Learning is simply making a computer perform a task without explicitly programming it. In today’s world, every system that does well has a machine Learning algorithm at its heart. Take for example Google Search Engine, Amazon Product recommendations, LinkedIn, Facebook etc. All these systems have machine learning algorithms embedded in their systems in one form of the other. They are efficiently utilizing data collected from various channels which helps them get a bigger picture of what they are doing and what they should do.
Cancel
I would request you to write more this type of article. 
Cancel
Hello
i started my classes for machine learning from a week and was soo confused about the main concept of machine learning. thanks to you and your article which helps me in understanding machine learning .
thank you
Cancel
eh?

Cancel
Share your comment.Thanks for sharing the article on machine learning. Processes involved in machine learning are similar to that of data mining and predictive modeling.With continued research into deep learning & AI we can expect more general applications.At nstar.in we delivered deep understanding of machine learning.
Cancel
Thanks for your Information About Machine learning training
Cancel
Nice blog about ML...
Cancel
Awesome blog. I enjoyed reading your articles. This is truly a great read for me. I have bookmarked it and I am looking forward to reading new articles. Keep up the good work!
Cancel

I don’t even understand how I finished up here, but I assumed this post was one of the great post i have read . please keep posting such article. 

Cancel

When it comes to machine learning it comes to a particular branch of computer science that can be considered a close relative of ‘ artificial intelligence.

Defining in a simple way the characteristics and applications of machine learning are not always possible since this branch is very vast and includes different methods, techniques, and tools to be realized.

Cancel
Really impressed! Everything is very open and very clear clarification of issues. It contains truly facts. Your website is very valuable. Thanks for sharing.
<a href="https://360digitmg.com/machine-learning-course-training-in-hyderabad">machine learning training</a>
<a href="https://360digitmg.com/artificial-intelligence-ai-course-training-in-hyderabad">artificial intelligence course 360DigiTMG</a>
Cancel
I think y’all should reach shadownethacker44@gmail.com    any type of legit hacking or database services they offer services on different range of issues and also helps to retrieve accounts that have been taken by by hackers.  or whatsapp him on +1 (781) 312-9232
Cancel

SearchBusinessAnalytics

SearchCIO

SearchDataManagement

SearchERP

Close