Machine Learning

Machine learning (ML) is a subfield of artificial intelligence (AI), defined in the 1950s by AI pioneer Arthur Samuel as “the field of study that gives computers the ability to learn without explicitly being programmed.” Machine learning is therefore broadly defined as the capability of a machine to imitate intelligent human behaviour. Artificial intelligence systems are programmed to perform complex tasks in a similar pattern to how humans solve problems. 

This means machines that can recognise a visual scene, understand a text written in natural language or perform an action in the physical world. Traditional programming used detailed instructions for the computer to follow. But in most cases, writing a program for the machine to follow is a complex task, for example, training a computer to recognise pictures of different people. While humans can do this task easily, it’s difficult to teach a computer to do it. 

Machine learning takes the approach of letting computers learn to program themselves through experience. The more data is fed into the machine the better the outcome. Computer programmers start my choosing a machine learning model to use, supply the data and let the computer model train itself to find patterns or make predictions. Over time the human programmer can also tweak the model, including changing its parameters, to help push it toward more accurate results. 

Neural networks are a commonly used, specific class of machine learning algorithms. Artificial neural networks are modelled on the human brain, in which thousands or millions of processing nodes are interconnected and organised into layers. In an artificial neural network, cells, or nodes, are connected, with each cell processing inputs and producing an output that is sent to other neurons. Labelled data moves through the nodes, or cells, with each cell performing a different function. In a neural network trained to identify whether a picture contains a cat or not, the different nodes would assess the information and arrive at an output that indicates whether a picture features a cat.

There are three subcategories of machine learning:

• Supervised machine learning models are trained with labelled data sets, which allow the models to learn and grow more accurate over time. 

• In unsupervised machine learning, a program looks for patterns in unlabelled data. Unsupervised machine learning can find patterns or trends that people aren’t explicitly looking for.

• Reinforcement machine learning trains machines through trial and error to take the best action by establishing a reward system. Reinforcement learning can train models to play games or train autonomous vehicles to drive by telling the machine when it made the right decisions, which helps it learn over time what is the correct action to take.

Deep Learning

The word “deep” explains the multi-layered aspect of machine learning and among all deep learning techniques, the most promising in the field of image recognition has been the CNNs. Yann LeCun, a prominent French computer scientist introduced the theoretical background to this system by creating LeNET in the 1980s, an automated handwriting recognition algorithm designed to read cheques for financial systems.

Since then, these networks have shown significant promise in the field of pattern recognition. Similar to radiologists that during the medical training period have to learn by constantly correlating and relating their interpretations of radiological images to the ground truth, CNNs are influenced by the human visual cortex, where image recognition is initiated by the identification of the many features of the image. 

Furthermore, CNNs require a significant amount of training data that comes in the form of medical images along with labels for what the image is supposed to be. At each hidden layer of training, CNNs can adjust the applied weights and filters — characteristics of regions in an image — to improve the performance on the given training data. However, deep learning requires a great deal of computing power, which raises concerns about its economic and environmental sustainability.