Scroll to top of page

Machine learning in a nutshell

The principle goal of machine learningmachine learningMachine learning is an artificial intelligence system that is based on the learning ability of algorithms. As this learning process relies on the repetition of an action, the accuracy of the results produced by machine learning algorithms improves over time.Learn more is to automate common tasks, with the help of computers. To do so, machine learning algorithmalgorithmAn algorithm is a mathematical process designed to solve a problem or to obtain a result, using a finite number of operations. It can be translated into a computer program thanks to a programming language.Learn mores try to mimic human learning based on a mathematical model. What is common to humans (e.g. recognising a face, lacing one’s shoes) is in fact a set of highly complex tasks for a machine.

The main idea behind machine learningmachine learningMachine learning is an artificial intelligence system that is based on the learning ability of algorithms. As this learning process relies on the repetition of an action, the accuracy of the results produced by machine learning algorithms improves over time.Learn more is that things that happened/coincided frequently in the past should happen/coincide in the future. For instance: if event B always happens after event A, you can expect to see event B happen shortly after event A.

Can machine learning beat the human mind? 

Of course, humans have many advantages over machines, including asking for an expert’s opinion, transferring knowledge from past experiences, and interacting with our environment to gather more information. But there are limitations to our capacities: we can be forgetful, or personally biased before making a decision. In order to mimic human thinking, machine learning must be done with human expertise and under supervision. Otherwise the model’s input could be totally random and the model would learn nothing.

In most cases, machine learning aims not to be better than a human, but to be able to address an issue well enough, but at scale. That is to say, the idea is that machines will be able to answer questions gathering lots of information faster than a human, and this possibly thousands or millions of times in a row. This volume is the main difference between traditional statistics (think good old linear regression via Excel) and modern machine learning. It is both the “length” (number of observations) and “width” (number of descriptors per observation) of the data that have changed the algorithmalgorithmAn algorithm is a mathematical process designed to solve a problem or to obtain a result, using a finite number of operations. It can be translated into a computer program thanks to a programming language.Learn mores, which exist only because we now have the required computational power.

For example, a machine learning algorithm can classify a product based on its outward appearance in a tiny fraction of a second whereas a human would need several seconds per product and would not be able to deal with hundreds of potential labels. Deep learning expert (& Director of AI at Tesla) Andrej Karpathy raced against machine learning on this task. It took Karpathy months, and he spent around one minute per image at the beginning. He reached a 5.1% error rate while GoogLeNet, the competing machine learning solution, reached a 6.67% error rate, but was able to answer immediately for each image. The machine learning solution is thus more suitable for production and scalability. Today’s solutions achieve a 3.46% error rate, and are both dramatically faster and more accurate than humans.

What are the differences among artificial intelligenceartificial intelligenceArtificial intelligence (often shortened to AI) is a subdiscipline of cognitive science. It refers to the technologies and methodologies that aim at building computer programs mimicking human intelligence and cognitive functions, including both human reasoning and perceptions.Learn more, machine learning and deep learning?

Performing complex tasks automatically is the goal of artificial intelligence. This can be addressed using different methods among which is machine learning. When dealing with abstract inputs like text, image, or audio, machine learning can be based on a specific family of algorithms called “deep learning” algorithms.

For instance, a smart vacuum cleaner that detects walls with captors is AI without machine learning. A smart vacuum cleaner that learns when to clean and where to clean more frequently, based on cleaning history, is AI that leverages machine learning (but without deep learning). Finally, if a smart vacuum cleaner is given a camera to detect your dog or your baby, the result is AI with deep learning.

Machine learning solutions can fall into 3 categories, which will be addressed in upcoming articles:

Want to learn more? Stay tuned!

Want to learn more? Get in touch!

18-01-2018

close legal

À propos

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Donec a venenatis dolor, non ornare ligula. Nam ultricies elementum tellus, sed pulvinar libero egestas nec. Fusce facilisis nulla vestibulum, commodo neque eget, dapibus lacus. Aliquam neque felis, sagittis nec consequat sed, commodo ac ipsum. Sed neque tortor, semper quis viverra et, malesuada et eros. Donec at dui ut ligula pharetra aliquet. Etiam dapibus semper orci. Integer efficitur dolor tortor, nec mattis elit placerat vel. Ut nulla enim, lacinia in pharetra id, convallis vitae massa. Donec neque est, tincidunt non ullamcorper commodo, tincidunt non turpis. Pellentesque viverra enim a sapien placerat, ut volutpat mauris condimentum. Proin tincidunt sollicitudin dui, sit amet condimentum ante commodo a. Aenean posuere aliquam purus, sed aliquam magna sagittis finibus. Morbi molestie feugiat feugiat. Phasellus tempus in dolor vel maximus. Cras efficitur sagittis lorem porta iaculis. Maecenas sed hendrerit urna. In mattis posuere purus, sit amet placerat arcu posuere quis. Etiam nec arcu nec magna interdum maximus. Integer sit amet lacus neque. Curabitur interdum molestie magna, in scelerisque tellus iaculis sed. Sed nec metus ut purus efficitur laoreet a quis eros. Proin dui dui, dignissim eget risus sit amet, bibendum condimentum velit. Maecenas in justo eu elit eleifend consectetur. Aenean scelerisque fringilla sollicitudin. Nam sem nibh, pharetra nec lacus non, mollis interdum odio. Aliquam sollicitudin posuere nibh sed eleifend.

Édition

55 SAS, 5 — 7 rue d'Athènes

75009 Paris

+33 1 76 21 91 37

Hébergement

OVH SAS

2, rue Kellermann

59100 Roubaix

+33 8 20 69 87 65

Publication

Lan Anh Vu Hong

Crédits photo

Mats Carduner, Adobe Stock & Unsplash

Vous avez aimé nos nouvelles fraîches sur l'état du marché brandtech ? Inscrivez vous à notre newsletter