Over the next couple of weeks, I plan to share all that I have so far learned on the topic of machine learning. Like many, I still consider myself a newbie to this field as I am still learning and exploring ways to improve my coding and writing skills. That being said, how about we start from the top?
What is machine learning?
Machine learning is a subfield of the larger topic of artificial intelligence, that is primarily concerned with pattern recognition. Additionally, we can also define machine learning as the science of getting computers to work explicitly without any form of human interfacing. The beauty and strength of ML is that it learns and improves from examples.
This is why when we do a web search, even before having finished entering a query, the search engine already provides us with alternatives. This is also why certain emails are sent to the spam folder, cause the system has been trained to pick up on or flag some key words that suggest it is spam. Furthermore, this is also why certain medical applications can pick up tumors or other anomalies that are not visible to the human eye from scans, and this really aids medical professionals in the diagnosis of diseases.
Machine learning has also led to one of the most significant and currently compelling areas, which is the field of deep learning. As has been said before, the advent of big data and access to more computational processing power has put DL at the forefront and really brought its attention to the public. We have seen improvements in natural language processing (NLP) through the introduction of the transformer architecture; we have also seen deep learning's applications to computer vision areas like video and image data through the creation of object detection algorithms like the very popular YOLO (You Only Live Once) program, and other architectures in the form of ResNets, the AlexNet and the also popular VGG network.
As previously mentioned, I plan to use this platform to share my ideas and learnings of my journey so far using this innovative and dynamic technology of machine learning, whereby we look into the history, theory and practicality of this science.
Top comments (0)