
Machine learning dates back to the 17th century. Machines can now learn tasks that were not programmed specifically for them. This allows us to train machines to work in unknown environments. What's the history behind machine learning? Continue reading to learn more. It is an important topic that engineers and computer scientists can both learn from. If you're interested in the history of machine learning, you'll appreciate this article.
Neural networks
Walter Pitts McCulloch and Warren Sturgis McCulloch, both neurophysiologists and mathematicians, first created artificial neural networks in 1943. Their work was key to the creation of neural networks. The two scientists proved that an input can be activated only if it is active by using logic gates. They were able to simplify brain functioning and open the door for machine learning.
Convolutional neural networks
Convolutional neural networks are made up of many layers of artificial neurons. Each neuron of the network is a mathematical operation that calculates a weighted combination of its inputs, outputs, and a value called activation. When given pixel values, the artificial neurons are taught to recognize different visual features. CNN has a first layer of convolutional layers. This layer contains the input image and generates activation maps. These maps highlight different parts of the image.

Boosting
Although the term "boosting" is not new, the phrase was first used to describe machine learning in 1990s. It is an algorithm that helps reduce bias during supervised learning, by transforming weak learners into strong ones. Robert Schapire introduced the concept of "boosting" in a 1990 paper. In that paper, he explained how to transform weak classifiers into stronger ones. Strong learners align well with the real classification while weak learners are only slightly correlated to the true classification.
Turing test
The Turing Test has become one of the most important concepts in the philosophy of artificial intelligence. Interrogating a computer with a question must produce an enquiry the machine cannot comprehend. Turing Test pass: If the machine is capable of producing such an enquiry, it is known to have passed. Problem with this test is its ability to attract projects whose main purpose is to fool the judges.
Deep learning
Machine learning and deep learning have a long history. It all started in 1965 when Valentin Grigoryevich Lapa and Alex Grigoryevich Ivakhnenko developed an algorithm that utilized polynomial activation function. The idea was replicate the brain's neural network by analysing data. However, research into artificial intelligence was not funded in the 1960s. Individuals still continued to work on this topic.
