I am delighted to learn about machine learning (ML), data science using Pandas, NumPy, Matplotlib, scikit-learn, and artificial intelligence (AI).
I intend to inspire someone else to pick up this skill by documenting my journey of learning these technologies as I progress through my roadmap.
Machine learning is a subset of AI, a machine that acts like humans and exhibits human intelligence. ML is an approach where AI tries to achieve artificial intelligence through systems that can find patterns in a data set.
ML comes in three parts:
- Data collection
- Data modeling
- Deployment
Therefore, ML is the science of getting computers to act without being explicitly programmed and is all about predicting results based on incoming data.
Deep learning is one of the techniques or algorithms for implementing machine learning.
To remember the most crucial concept of ML, you need to do the following with your data:
- Train your model
- Validate or tune your model
- Test and compare the data set
Exercise
Train a computer to recognize your images, sounds, and poses. Use this resource to gain a better understanding.
Tools and Technologies
Resources
In the next lesson, I will learn about using Pandas for data analysis, such as describing, viewing, selecting, and manipulating data.
See you there!
Top comments (4)
What is machine learning?
Machine learning is a subset of AI, a machine that acts like humans and exhibits human intelligence. ML is an approach where AI tries to achieve artificial intelligence through systems that can find patterns in a data set.
You are correct that ML is a subset of artificial intelligence (AI), because not all AI involves ML.
AI includes any technique which enables computers to mimic human behavior, while ML is specifically about algorithms that learn from data to mimic human behaviour e.g. classification, anomaly detection, natural language understanding et cetera.
I think ML involves algorithms that can learn patterns and make decisions with minimal human intervention, but it still requires significant programming effort, especially in designing algorithms and selecting appropriate data.
I understand your point of view. Thanks for the clarification.