DEV Community

Neha Gupta
Neha Gupta

Posted on

10 1

Day 1 of 30 : Machine Learning

Hey everyone I have started studying about machine learning and decided to share my journey with you guys.
So today as it was my first day I got to know about the term Machine Learning and some of its fundamentals which I am sharing in this post.

What is Machine Learning?

Machine Learning is a branch of Artificial Intelligence that gives computers the ability to learn without explicitly being programmed.
It was defined in the 1950s by AI pioneer Arthur Samuel as “the field of study that gives computers the ability to learn without explicitly being programmed.”

Types of Machine Learning

Machine Learning is broadly categorized in 4 types ->

  1. Supervised Machine Learning -> In supervised machine learning the data is labeled ,meaning each example comes with a correct answer ,and the machine is trained on this data and a model is generated which gives accurate prediction for similar kind of data. For example training the machine for a given set of pictures of trees, flowers, leaves etc. labeled properly and after getting perfectly trained when a new similar input is given machine makes a prediction.

  2. Unsupervised Learning -> In unsupervised learning the data is not labeled the machine learns by identifying pattern in data. In an unsupervised learning process, the machine learning algorithm is left to interpret large data sets and address that data accordingly. The algorithm tries to organize that data in some way to describe its structure.

  3. Reinforcement Learning -> Reinforcement machine learning trains machines through trial and error to take the best action by establishing a reward system. For example a robot is given some instructions ,whenever it takes a wrong decision it learns from it and for every right decision it is rewarded.

  4. Semi Supervised Machine Learning -> Semi-supervised learning is similar to supervised learning, but instead uses both labelled and unlabeled data. In semi-supervised learning, the algorithm learns from a dataset that contains a small amount of labeled data and a much larger amount of unlabeled data.

Apart from theoretical part I learnt little about math's part also which I'll share in my next post till then stay connected :)

Image of Timescale

🚀 pgai Vectorizer: SQLAlchemy and LiteLLM Make Vector Search Simple

We built pgai Vectorizer to simplify embedding management for AI applications—without needing a separate database or complex infrastructure. Since launch, developers have created over 3,000 vectorizers on Timescale Cloud, with many more self-hosted.

Read more

Top comments (6)

Collapse
 
karenlynn8 profile image
Kar

Love this! Is this part of a course or a self guided tour? 😊

Collapse
 
ngneha09 profile image
Neha Gupta

Yes

Collapse
 
ngneha09 profile image
Neha Gupta

It is self guided tour

Collapse
 
aatmaj profile image
Aatmaj

All the best for your journey!

Collapse
 
ngneha09 profile image
Neha Gupta

Thanku so much :)

Collapse
 
priso profile image
Priyalll

Loved the blog !

Billboard image

Create up to 10 Postgres Databases on Neon's free plan.

If you're starting a new project, Neon has got your databases covered. No credit cards. No trials. No getting in your way.

Try Neon for Free →

AWS GenAI Live!

GenAI LIVE! is a dynamic live-streamed show exploring how AWS and our partners are helping organizations unlock real value with generative AI.

Tune in to the full event

DEV is partnering to bring live events to the community. Join us or dismiss this billboard if you're not interested. ❤️