Today I will explain what Machine Learningis in a couple of minutes.
Hello everyone, I am Riccardo Osti and ona daily basis I help the world’s best brands become more profitable by investing in theconsumer experience If you didn’t subscribe to my channel pleasedo it right now.
You will receive an email every time I publisha new video.
Historically we have been told that computersneed to be programmed in order to perform specific tasks, however, in recent years,scientists have developed algorithms that make possible for computers to act, basedon patterns and statistical trends instead of commands programmed by us, the humans.
In short, Machine learning algorithms usehistorical datasets to make predictions and decisions without being programmed for them.
Machine learning is particularly useful forapplications where it wouldn’t be feasible to create different algorithms to performall the specific tasks.
A good example is computer vision, where algorithmsmay need to understand if a certain object is in a picture or not.
Instead of coding the many different characteristicsof that object, machine learning would start by analyzing a vast amount of pictures withthat object in them, to identify similarities that would help to identify that object inthe future.
Let’s make a simple example: we want toidentify photos of sunny days.
We would then give the algorithm a datasetwith photos of clear blue skies and with photos of rainy days.
The algorithm would identify the similaritiesof these two separate datasets, such as colors, brightness, tone, et cetera.
After this learning process, the machine wouldbe able to decide whether a photo represents a sunny day or not.
Usually, the quality of machine learning decisionsis related to the size and quality of the training datasets.
In fact, Machine learning algorithms heavilyrely on statistics, where it is easier to make decisions upon large historical datasets.
Challenges of machine learning are usuallyrelated to the lack of good training datasets, and to the capability of the algorithms toreach very high levels of accuracy which are required for certain applications.
For example, in 2018, a self-driving car fromUber failed to detect a pedestrian, who died in the accident.
I hope you like this type of videos whereI try to explain complex concepts with simple words in just a couple of minutes.
Let me know in the comments! See you soon!.