Start a team blog
Start a team blog, invite your team, and start publishing.
I decided to write weekly

I decided to write weekly

Shreyas Kulkarni
·Jan 15, 2022·

4 min read

As the title says I decided to write about my weekly learnings, so the obvious question that came into my mind was why? and the simple answer is I want to cultivate the habit of constant learning and reflecting on what I learned and blogging is the simplest way to track the trajectory and in general my favorite Twitter account always emphasis on writing for better clarity so I am starting here!

In the first week of January I decided to start learning machine learning from the very basics, the initial few days have gone into an exploration of available resources out there on the internet and I am now convinced with the fact that no course will ever provide you all the information you need. so rather than going with the most recommended courses I will be going with whatever suits me best.

After completing some popular playlists on YouTube and exploring some Udemy courses I found Coursera suitable for me in case of machine learning, right now I am learning through Coursera, Introduction to Applied Machine Learning by Alberta Machine Intelligence Institute

So far I have completed my first week, so I am going to stick to the basics and gradually learn further.

we often see confusion with what exactly is AI and Machine Learning, both terms look alike there is limited clarity around these terms.

formally AI is...about finding solutions to specific tasks without the solution being explicitly programmed.

Traditionally computers only do what you tell them, so you have to program each step exactly, while with the use of AI the core problem getting solved is letting computers take their own decision so programmers won't have to explicitly intervene and do changes often, AI will take care of these changes and build its own understanding about how to navigate and deal with the situation.

Machine Learning is a subset of AI, based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

Machine learning’s rise to prominence today has been enabled by the abundance of data, more efficient data storage, and faster computers.

Depending on what you are trying to accomplish, there are many different ways to get a computer to learn from data. These various ways can be categorized into three main subsections of machine learning: supervised learning, unsupervised learning and reinforcement learning.

The core idea behind supervised learning is that you provide labeled data to the algorithm and it will attempt to determine the label of new unlabeled examples it will be totally based on the labeled examples that you've already provided. Supervised learning problems include: Classification and Regression

Unsupervised learning is when we are dealing with data that has not been labeled or categorized. The goal is to find patterns and create structure in data in order to derive meaning.

Reinforcement learning, the algorithm uses past experience to choose actions in the present, it focuses on taking suitable action to maximize reward in a particular situation as well as avoid punishments. popularly when you don't have correct answers but you can define some signal for success, reinforcement learning is the framework you need.

Apart from popular categories these following are a few of the learning techniques:

Semi-Supervised Learning

In semi-supervised learning, data scientists combine the two. A model uses unlabeled data to gain a general sense of the data’s structure, then uses a small amount of labeled data to learn how to group and organize the data as a whole. The advantage of this approach is that often the quantity of labeled data needed for learning a good model may be reduced, as there is an opportunity to learn from the contextual information provided by unlabeled data.

Transfer Learning

Transfer learning is essentially transferring knowledge from one task to another. Humans are very good at this. so the basic idea behind transfer learning is using a pre-trained network instead of just trying to train it on just your data.

This week I found this interesting video showcasing How data transforms the decisions

A short 6 minutes video about how NBA uses data to level up in their games!

That’s all for starting with Machine Learning! Keep your eye out for more blogs coming soon that will go into more depth on specific topics.

You can always connect with me Here😃