Machine Learning (ML) กับ Deep Learning (DL)

What's the difference between Machine Learning (ML) and Deep Learning (DL)? 🧐

🧠 Machine Learning (ML)

Is "the kind of learning we need to guide."

- Inputs: We feed the raw data (blue circle) into it.

- Feature Extraction (Feature Extraction): This is the key point! "People" (Ourselves)

You have to think about and choose what properties are important in that information.

Like we teach a child, "Look here...Notice here. "

- Learning: The machine then "learns" from the properties we choose to enter.

- Outputs: And then give out the "results."

ML summary: People help choose "what to know" - > Machines learn from that.

🚀 Deep Learning (DL) - (lower image)

Is "self-thinking learning" (part of better ML).

- Inputs: We entered the raw data (blue circle) into it as before.

- Feature Extraction + Learning: The dots are here! We don't have to tell you what's important. The machine will "learn and extract all of its own important properties through more complex" neural networks. "

- Outputs: And then give out the "results."

Summary DL: We enter raw data - > all self-thinking and learning machines.

* * Summary:

- ML: We must enter the key "knowledge / features" to the machine first.

- DL: The machine discovers knowledge / properties on its own.

Deep Learning often excels at very complex tasks, such as distinguishing faces in pictures, understanding languages, or driving automatically, because it can find very complex "features" without the need for a guide!

# MachineLearning # DeepLearning # AI # Data Science # Technology