Fennaio | learn about artificial intelligence


What is Machine Learning?

Machine Learning is at the heart of Artificial Intelligence. This incredible technology allows systems to literally learn, as opposed to being told exactly what to do, and as such, is highly dynamic, variable and capable of handling, and learning from, hugely diverse types of data in multiple scenarios and environments.

In this section we will discuss succinctly the key points about Machine Learning.

Suggested supplementary reading: What is Artificial Intelligence?

Suggested supplementary reading: What is an Artificial Neural Network?

In a nutshell

Machine Learning has the overall goal of taking data as an input and working out how all this data is linked to ultimately come up with an output. In doing so, much like how the brain operates, it has learnt how a set of circumstances (whether they be data, observations or actions) leads to a desired or undesired outcome.

When the AI/ML system has learnt these links (known as trained/training) it can then be supplied with new/current data to accurately predict an outcome, based on how it knows data is linked and related. This is where the power lies in Machine Learning - the ability to predict an outcome based on past highly variable experiences.

Machine Learning is a Broad Subject

Technically speaking, Machine Learning involves a computer running an algorithm in order to learn something, and this algorithm could be diverse in terms of autonomy, the variability of data it can handle and the predictions it can make.

It could be, in the simplest form, an algorithm derived by a data scientist looking at a specific dataset and looking for specific patterns to learn over time, or at the other extreme it could be a computer model of the human brain (Artificial Neural Network) learning from any set of diverse data thrown at it.

Machine Learning that runs specific data-science derived algorithms, although they are certainly learning, are deemed low level Artificial Intelligence as they are looking for specific patterns in specific data and are usually continually finely tuned by human operators - therefore offer relatively low levels of autonomy and variability.

On the other hand, Machine Learning that uses Artificial Neural Networks is the most high level Artificial Intelligence approach, as the system is not only more powerful in terms of being able handle and link extremely diverse data (the same neural network can be used on all types of data), but is able to function with very little (or no) input from a human observer. Artificial Neural Networks are made up of Artificial Neurons that combine in layers (input layer, hidden layer(s) and output layer) to form a network of neural connections that model the basics of how the human brain works. These ANNs are modelled using mathematical algorithms that have the sole aim of working out how an output is achieved from a set of inputs - as quickly as possible. Artificial Neurons are linked to each other using a weighting system. They each receive inputs, process them, change their state, and then output to the next neuron using different degrees of influence, much like the brain does. The process is repeated many times until the system has been trained and primed ready to accept subject data to predict from.

The Machine Learning Process

Whatever type of Machine Learning is employed, whether it's a straightforward statistical algorithm or an Artificial Neural Network, numerical data (generally normalised and converted from alphabetical data if required) is utilised as the input and Machine Learning processes use this data to learn from using three approaches, in order to link the data within, assess the relationships, and come up with an output.

Types of Learning

Supervised, Unsupervised and Reinforcement Learning

When an AI system is learning, the term is Training and in Machine Learning it happens in one of three ways:

Supervised Learning

In supervised learning - The most common form of AI learning - AI is supplied with data where we know what the inputs and output fields are and the AI uses Machine Learning to link known inputs with known outputs. e.g. in a very simple case we may have inputs of "Age", "Post Code", "Education Level", "Credit Score" and simple outputs of "Good Customer" and "Bad Customer" based on our historical data. AI would learn the links between all these data so that when we pass it information of a potential customer it will be able to tell us if this customer is likely to be "Good" or "Bad". In reality, you would likely have dozens, hundreds or even thousands of inputs from which the AI will learn from - which is why it's so powerful - making links that a human or traditional computer program would simply not be able to do in the same time frame.

Unsupervised Learning

Here, AI is supplied with data as above however it doesn't know what fields make up the inputs or outputs - it is up to Machine Learning to learn these combinations by e.g. working out the links between all fields and looking for correlations.

Reinforcement Learning - also known as Reward-based Learning

Here AI again learns through Machine Learning, however it learns by rewarding itself if it gets a particular action correct. It does this by firing off an action and then comparing the environmental state before and after the action - this type of learning has been used to successfully train AI systems to play computer games by vision alone, based on learning thousands of screen actions performed by a human player.

Machine Learning Software

Fennaio designs, develops and provides Machine Learning software than can be used for all Artificial Intelligence systems.

We have available off-the-shelf turnkey Machine Learning/AI software and can create bespoke software solutions where required.

Please get in touch with us to discuss your Machine Learning requirements.

What is Machine Learning? - Key Points

  • Machine Learning is at the heart of Artificial Intelligence
  • Machine Learning can be a relatively simple data-science-derived statistical algorithm, or it could be a model of the human brain by using Artificial Neurons, arranged and mathematically linked in layers (input, hidden and output layers)
  • The actual learning process is called Training
  • Training can take place using supervised, unsupervised and reinforcement learning
  • The ultimate goal of Machine Learning is work out how a variable input dataset leads to an output by working out the data relationships between fields in the dataset
  • A trained Artificial Neural Network which has learnt from historical data can be given current data in which to make a prediction from
  • Machine Learning is thousands, if not millions times more efficient than using a standard software approach or using humans to achieve the same goal in an equivalent timeframe

Learn more

Thanks for reading about Machine Learning, there's more to learn below:

How Fennaio works with you at every stage of the AI and ML Integration process.

Whether you are starting out on your first AI project, just interested in the possibilities of AI or are wanting to expand your existing AI suite, we are here to help.

AI Survey & Plan

We will discuss with you where you are, where you want to be, and how we can achieve it with AI - whether by a bespoke solution or using one of our off-the-shelf products

AI Data Analysis & Preparation

We will work with you to gather, analyse and prepare all your relevant data sources for use in the AI system(s)

AI Execute & Visualisation

We will run and tune the AI throughout the AI learning process and enable the AI to produce a real time visual output to confirm the AI is producing beneficial results

AI Integration

When you are satisfied the AI is delivering the results you desire, we will integrate the AI with your new or existing systems

You are one step closer to getting Artificial Intelligence into your organisation

Fennaio has the expertise to get you up and running with AI, Machine Learning, Deep Learning and Data Science in your new or existing systems, software and operations.

Get Started
no to gdpr