What does Machine Learning mean?

In recent years machine learning is gaining more and more popularity, but what exactly is the Machine Learning. in this section we will deep dive and answer all this question by the end of the topic you will understand what machine learning is, types and how machine learning is used.

Evolution of Machine Learning

The name Machine Learning initially originated from famous gaming researcher Arthur Lee Samuel. Samuel is the first person to bring self-learning programs into society. This remarkable discovery shortly laid the foundation for Machine Learning algorithms. In later years raising popularity in Machine Learning and Artificial Intelligence give birth to so many innovations in the field of Computers and Automation, However, similar definitions and usage of ML & AI created ambiguity in distinguishing these two fields. In fact, few beginners in this field often use AI and Machine Learning interchangeably, but the fact is that they are the same.

Artificial Intelligence is the integration of machine learning algorithms. Artificial Intelligence models are used to perform multiple tasks such as Self driving cars, Humanoid Robots

On the other hand, Machine Learning is used to accomplish only specific tasks like spam detection, Movie recommendation, and Image classification.

Actually, Machine Learning is a subfield of AI, the picture below clearly explains what I meant.

Machine learning is broadly segmented into three types.

Supervised Machine Learning

Unsupervised Machine Learning

Reinforcement Learning 

Supervised machine Learning

Supervised machine learning is the most commonly used technique many industries use supervised machine learning techniques to train machine learning algorithms

In supervised Machine Learning, we supervise or teach the machine using labeled data, in other words, we show the sample data and tell the machine what the label is, likewise we do it for every sample in the dataset.

Figure 1 will clearly explain the working of supervised machine learning.

In figure 1 Dataset consists of ‘n’ Labelled cat and dog images, each image is labeled with a tag. For instance, in figure 1 Image 1 is labeled as a cat. Likewise, there will be ‘n’ labeled images from 1 to n.

In supervised learning, the Teacher holds the actual values for every corresponding image in the dataset. Similarly, the Learning system will give predicted values for every corresponding image in the dataset. Once we got the image output values from the teacher and learning system error function will calculate the error between actual and predicted values.

Using the feedback error, the Learning system will keep on updating its parameters (weights) to minimise the error value. Eventually, this process of learning parameters (weights) will help the Learning system to understand the model.

Unsupervised Machine Learning

In contrast to Supervised Machine learning, unsupervised machine learning doesn’t have any monitoring or teaching system. we let the machine to figure out its own model from unlabeled data.

Like figure 1, In figure 2 also Dataset consists of ‘n’ images of Cats and dogs but now this image is unlabeled (means we don’t mention their tags to learning system), for instance, in figure 2 now Image 1 is unlabeled it may be cat or dog. Likewise, there will be ‘n’ unlabeled images from 1 to n.

So, to tackle this unsupervised learning system uses the concept of clustering, Clustering is a grouping technique in which similar featured objects are grouped together. In the above example figure 2, we have two different categories (cats vs dogs), accordingly, we design our learning system capable of clustering into two groups of images separately. we achieve this by the concept of feature selection in other words similarly in images are grouped together and dissimilar images group together. 

Reinforcement Learning

Reinforcement learning is a special type of machine learning especially used for game theory, signals and system and control systems.

What next

Most Machine Learning algorithms fall under these categories, but current advancement in machine learning created many more different algorithms among them Semi-Supervised Learning is worth of mentioning.

Why and where we use Machine learning

According to Forbes Machine Learning is going to a common buzzword in Medical, Finance, Transportation, E-commerce and many more sectors.

But why popular Companies are focusing on machine learning nowadays.

The answer is because of machine learning capabilities.

Do you know how Amazon is achieved to show the same product that you saw on their website last night and have you ever thought how Netflix able to recommend the movies you are interested in, the simple answer is Machine learning algorithms, this algorithm is expertise in the forecast the future trends and understands the customer behavior.

Likewise, there are a lot of applications of Machine learning in different fields

Computer vision

+ posts

Meet Stella


Related articles

The value of colocation data centres in IoT

IoT data processing is increasingly being pushed out to the network edge to get as close as possible to the source sensors and end-users of the resulting data analytics

Strategy and anticipation are key to securing against cyber threats

With technological progress comes increased security risks. Sophisticated and co-ordinated cyber groups are working every day to find potential entry points into organisations’ networks.

Raising talent attraction and retention with IT investment

To be at the centre of talent attraction and retention, businesses should make use of workplace technology that enables them to integrate collaborative, secure and sustainable measures into their operations.

How NIST started the countdown on the long journey to quantum safety

Leading the charge to develop a post-quantum cryptographic standard for organisations is the US government’s National Institute of Standards and Technology (NIST).

Overcoming economic uncertainty with cloud flexibility

Particularly for companies that jumped into the cloud headfirst, taking the time to optimise existing processes is a remarkable way to reduce infrastructure costs and free up OPEX for delivering business value.

Subscribe to our Newsletter