I thought Supervised and Unsupervised learning both come under Machine learning. But when Andrew explains the 'Different Terminologies of AI", it feels like he is equating ML to supervised learning meaning A to B.
The venn diagram also shows it.
What am I missing?
Hello Aravind. Thanks for asking this. I was intrigued to answer you, but as a beginner I’m not sure if I understand it correctly. I’m looking forward to the answer of a Mentor or team member. Good luck with your learning journey!
I don’t think ‘unsupervised learning is not machine learning’ is the right takeaway from this lecture. The focus is on differentiating machine learning from data science, not of differentiating supervised learning from unsupervised learning, the latter of which is barely referenced. You can find many sources that list supervised, unsupervised and reinforcement as the 3 types of machine learning. Notice that unsupervised and reinforcement are lumped together under the other buzzwords bullet on the slide at the 8:00 mark.
There is plenty more said about unsupervised learning in other lectures, and it makes up a good portion of the content of the Machine Learning Specialization, so I wouldn’t get too caught up in how the terms are used in this early, very high level discussion.
Supervised learning, also known as supervised machine learning, is a subcategory of machine learning and artificial intelligence .
Thanks for your question.
I’m not sure I fully understand your question, but I’ll try to delve into the topics covered in Andrews’ lecture to convey a broader view of the concepts at hand.
Machine Learning:
Machine Learning is a field of artificial intelligence that empowers computers to learn patterns from data and make predictions or decisions without explicit programming. It encompasses diverse techniques such as supervised learning, unsupervised learning, reinforcement learning, and more. While Andrew Ng’s explanations and Venn diagrams might focus on supervised learning as an introductory concept, it’s crucial to understand that Machine Learning extends beyond just supervised learning.
Supervised Learning:
Supervised learning is a subset of Machine Learning where algorithms learn from labeled training data, mapping input features to corresponding output labels. This method is used for tasks like classification and regression, where the algorithm generalizes patterns to make predictions on new, unseen data. Supervised learning requires labeled examples to guide the learning process, enabling algorithms to minimize prediction errors during training.
Unsupervised Learning:
Unsupervised learning, another subset of Machine Learning, involves finding patterns and structures within unlabeled data. Unlike supervised learning, there are no explicit output labels to guide the learning process. Instead, algorithms focus on discovering inherent relationships and groupings within the data. This technique is commonly used for tasks like clustering and dimensionality reduction, helping to uncover hidden insights and patterns within complex datasets. Unsupervised learning doesn’t require labeled data but relies on the intrinsic structure of the data itself.
I hope this help
Best regards
elirod
Welcome to the community.
ML is Supervised Learning A to B