What is Machine Learning?
“An agent is said to learn from experience with respect to some class of tasks and a performance measure P if the learner’s performance at tasks in the class as measured by P improves with experience”. This type of learning where we learn from experiences is called Inductive learning.
Get Ishita Tandon’s stories in your inbox
Join Medium for free to get updates from this writer.
This concept of inductive learning when applied to machines like computers is known as Machine Learning.
ML Paradigms
- SUPERVISED LEARNING: Learn an input and output map. This can further be classified into- Classification: Categorical output and Regression: continuous output.
- UNSUPERVISED LEARNING: Discover patterns in the data. These can further be classified into- Clustering: Cohesive Grouping and Association: Frequent occurrence.
- REINFORCEMENT LEARNING: Learning by its own
The various questions to keep in mind while building a machine learning model
- How good is a model?
- How do I choose a model?
- Do I have enough data?
- Is the data of sufficient quality? Does it have errors or missing values?
- How confident can I be of the results?
- Am I describing the data correctly?
I will be answering all these questions in subsequent articles, so stay tuned!
Hi, My name is Ishita. I am an electrical engineering undergrad at the National Institute of Technology. I took the initiative to write a blog because when I started learning programming I faced obstacles finding the right sources. Now I want to share my knowledge with everyone stepping into learning programming for Data Science to make it easier for them. Honestly, I am no expert but feel free to join me along my journey as we both learn together. You can connect with me on LinkedIn.
