Machine Learning
What is Machine Learning?
The term Machine Learning was coined by Arthur Samuel in the year 1959. He was a pioneer in Artificial Intelligence and computer gaming, and defined Machine Learning as “Field of study that gives computers the capability to learn without being explicitly programmed”. In this article, we will explore in detail about machine learning.
Simply put, Machine Learning is the study of making machines more human-like in their behavior and decisions by giving them the ability to learn and develop their programs. This is done with minimum human intervention, i.e., no explicit programming. The learning process is automated and improved based on the experiences of the machines throughout the process. Good quality data is fed to the machines and different algorithms are used to build ML models to train the machines on this data. The choice of algorithm depends on the type of data at hand, and the type of activity that needs to be automated.
Here’s a video by explaining what is Machine Learning from the ground up.
Now you may wonder, how is it different from traditional programming? Well, in traditional programming we would feed the input data and a well written and tested program into a machine to generate output. When it comes to machine learning, input data along with the output is fed into the machine during the learning phase, and it works out a program for itself. To understand this better, refer to the illustration below:
Types of Machine Learning
In this section, we will learn about the different approaches towards machine learning and the type of problems they can solve.
Supervised Learning:
It is the widely used approach in a maximum of the Machine Learning applications. The supervised learning model has a set of input variables (x), and an output variable (y). An algorithm is used to identify the mapping function between the input and output variables. The relationship is y = f(x).
The learning is monitored or supervised in the sense that we already know the output and the algorithm is corrected each time to optimize its results. The algorithm is trained over the data set and corrected repeatedly until it achieves an acceptable level of performance.
Supervised learning problems can be further grouped as:
- Regression problems — Used to predict future values and the model is trained with the historical data. Eg: Predicting the future price of a product.
- Classification problems — The algorithm is trained with various labels to identify items within a specific category. Eg: Disease or no disease, Apple or an orange, Beer or wine.
Here’s a video that describes step by step guide to approaching a Machine Learning problem with a beer and wine example:
Unsupervised Learning:
This approach is the one where the output is unknown and we have only the input variable at hand. The algorithm is left to learn by itself and discover interesting structure in the data.
The goal is to decipher the underlying distribution in the data to gain more knowledge about the data.
Unsupervised learning problems can be further grouped as:
- Clustering: This is used to group the input variables with the same characteristics together. Eg: grouping users based on search history
- Association: Here we discover the rules that govern meaningful associations among the data set. Eg: People who watch ‘X’ will also watch ‘Y’
Semi-supervised Learning:
Here the data is trained on a mix of a very small amount of labeled data and a large amount of unlabelled data. Usually, the first step is to cluster similar data with the help of an unsupervised machine learning algorithm. The next step is to label the unlabelled data using the characteristics of the limited labeled data available. Once the complete data set is labeled, the supervised learning algorithms can be used to solve the problem.
Reinforcement Learning:
In this approach, machine learning models are trained to make a series of decisions based on the rewards and feedback they receive for their actions. The machine learns to achieve a goal in complex and uncertain situations and is rewarded each time it achieves it during the learning period.
Reinforcement learning is different from supervised learning in the sense that there is no answer available so the reinforcement agent decides the steps to perform a task. When the training data set is not present, the machine is bound to learn from its own experiences.
Machine Learning Applications
Machine Learning algorithms help in building intelligent systems that can learn from their past experiences and historical data to give accurate results. Many industries are thus applying machine learning solutions to their business problems, or to create new and better products and services. Some of the applications of Machine Learning can be seen in healthcare, defense, financial services, marketing, and security services among others. Some of them are described below:
Facial recognition/Image recognition: The most common application of machine learning is Facial Recognition and the simplest example of this application is the iPhone X. There are a lot of use-cases of facial recognition, mostly for security purposes. It can be used to identify criminals, find missing individuals, aid forensic investigations, etc. Apart from this, it is being used in intelligent marketing, diagnose diseases, track attendance in schools, and more.
Automatic Speech Recognition: Abbreviated as ASR, automatic speech recognition is used to convert speech into digital text. Its applications lie in authenticating users based on their voice and performing tasks based on the human voice inputs. The system is trained by feeding speech patterns and vocabulary to train the model. Presently ASR systems find a wide variety of applications in the following domains:
– Medical Assistance
– Industrial Robotics
– Forensic and Law enforcement
– Defense & Aviation
– Telecommunications Industry
– Home Automation and Security Access Control
– I.T. and Consumer Electronics
Financial Services — Machine learning has many use cases in Financial Services. Machine Learning algorithms prove to be excellent at detecting fraud by monitoring activities of each user and assess that if an attempted activity is typical of that user or not.
Financial monitoring to detect money laundering activities is also an important security use case of machine learning.
Machine Learning also helps in making better trading decisions with the help of algorithms that can analyze thousands of data sources simultaneously. Other applications include, but are not limited to, underwriting and credit scoring.
The most common application that is witnessed in our day to day activities is the virtual personal assistants like Siri and Alexa.
Marketing and Sales: Machine Learning is improving lead scoring algorithms by including various parameters such as website visits, emails opened, downloads, and clicks to score each lead.
It also helps businesses to improve their dynamic pricing models by using regression techniques to make predictions.
Sentiment Analysis is another important application to gauge consumer response to a specific product or a marketing initiative.
Machine Learning for Computer Vision helps brands identify their products in images and videos online. This is used to measure the mentions that are posted without any relevant text.
Chatbots are also becoming more responsive and intelligent with the help of machine learning.
Healthcare — An important application of Machine Learning is in the diagnosis of diseases and ailments which are otherwise difficult to diagnose. Radiotherapy is also becoming better with Machine Learning taking over.
Early-stage drug discovery is another important application that involves technologies such as precision medicine and next-generation sequencing.
Clinical trials cost a lot of time and money to complete and deliver results. Machine Learning-based predictive analytics could be applied to improve on these factors and give better results.
Machine Learning technologies are also critical to make outbreak predictions and are being used by scientists around the world to predict epidemic outbreaks.
Recommendation Systems — Many businesses today use recommendation systems to effectively communicate with the users on their site. There is a lot of learning in the user behavior data that can be applied to recommend relevant products, movies, web-series, songs, and much more.
Most prominent use-cases of recommendation systems are e-commerce sites like Amazon, Flipkart, and many others along with Spotify, Netflix, and other web-streaming channels.
Machine Learning Jobs and Career prospects:
Before moving on to Machine Learning job roles and career prospects, let us have a look at the skill sets that are necessary to become a successful machine learning professional.
The prerequisites to learn Machine Learning are:
– Linear Algebra
– Statistics and Probability
– Calculus
– Graph theory
– Programming Skills — Python, R, MATLAB, C++ or Octave
Essential Machine Learning skills to become a successful ML professional are:
Machine Learning Algorithms and Libraries — There is an absolute need to be acquainted with the implementation of ML algorithms mostly available through APIs, Packages, and Libraries. It is also important to learn about the pros and cons of different applicable approaches towards ML implementation.
Data Modelling and Evaluation — This includes the process of continuously evaluating the performance of the given model. This is achieved by selecting an appropriate accuracy measure and an effective evaluation strategy based on the problem at hand.
Distributed Computing — Machine Learning jobs require to be working with a great set of data. This large amount of data cannot be processed using a single machine. It needs to be distributed across a cluster of machines.
Software engineering and system design — A strong base in software engineering and system design is a requisite for a successful machine learning career. The ability to build appropriate interfaces for components is preferred by employers. These skills are valuable for improving quality, productivity, collaborations, and maintainability.
Machine Learning Job Roles and salary trends:
The future scope of Machine Learning
It is estimated that the Machine Learning market will grow to reach USD 8.81 billion by the year 2022. That means that there is going to be a substantial requirement of skills around Machine Learning to drive this growth. The future looks promising for those planning a career in Machine Learning!
If you want to know more about what is machine learning and are interested in pursuing a career in Machine Learning, check out Great Learning’s postgraduate program in Machine Learning.
