Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Akshay 🚀 Profile picture
@akshay_pachaar
Nov 10 • 8 tweets • 3 min read Twitter logo Read on Twitter
AI Engineering is going to be a high leverage skill!

Here's a complete roadmap to become an AI Engineer (No-shortcuts)!

What's covered:

- Python
- Prompt Engineering
- LangChain & VectorDBs
- Retrieval Augmented Generation
- Finetuning & Deploying LLMs at Scale

Read more...👇 Image
1️⃣ Python: Harvards's CS50AI

CS50's Introduction to Artificial Intelligence with Python!

You'll learn:

- Machine learning
- Artificial intelligence principles
- How to use AI in Python programs
- How to design intelligent systems

Check this out👇
pll.harvard.edu/course/cs50s-i…
2️⃣ Prompt Engineering Guide

Zero/Few shot prompting is what makes LLMs so powerful!

However, the quality of their response largely depends on how well you craft your prompt.

Here's an excellent guide to mastering prompt engineering!

Check it out👇
promptingguide.ai
3️⃣ LangChain & VectorDBs

@activeloopai created the most in-depth & easy-to-follow course on building with LLMs using LangChain & VectorBDs

• 50+ Lessons
• 10+ Projects you could use in production
• Challenging and fun Quizzes

Enroll for FREE!👇
learn.activeloop.ai/courses/langch…
4️⃣ RAGs:

LLMs hallucinate, producing wrong outputs and their knowledge is limited to the data they are trained on!

We use Retrieval Augmented Generation to over come this limitation!

Here's a blog that quickly introduces RAGs & LlamaIndex:
mlspring.beehiiv.com/p/rags101-intr…
5️⃣ Fine-tuning LLMs

This is the most comprehensive & hand-on course I have seen on:

- Training
- Fine-tuning
- And deploying LLMs

Enroll for FREE!👇
learn.activeloop.ai/courses/llms
6️⃣ LLM Learning Lab by @LightningAI

A curated collection of blogs, tutorials, and how-to videos on:

- Training
- Fine-tuning
- And deploying LLMs 🚀

Actively maintained and includes all the recent advancements in the LLMs space.

Check this out👇
lightning.ai/pages/llm-lear…
That's a wrap!

If you interested in:

- Python 🐍
- ML/MLOps 🛠
- AI Engineering ⚙️

I write a weekly newsletter focused on AI Engineering!

You can subscribe here for FREE!👇
mlspring.beehiiv.com/subscribe

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Akshay 🚀

Akshay 🚀 Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @akshay_pachaar

Akshay 🚀 Profile picture
Nov 9
Object oriented programming is essential for writing clean & modular code!

Today, I'll clearly explain OOPs with Python!

Let's go! 🚀 Image
We break it down to 6 important concepts:

- Object 🚘
- Class 🏗️
- Inheritance 🧬
- Encapsulation 🔐
- Abstraction 🎭
- Polymorphism 🌀

Let's take them one-by-one... 🚀
1️⃣ Object 🚘

Just look around, everything you see can be treated as an object.

For instance a Car, Dog, your Laptop are all objects.

An Object can be defined using 2 things:

- Properties: that describe an object
- Behaviour: the functions that an object can perform

...👇
Read 11 tweets
Akshay 🚀 Profile picture
Nov 8
Two of the fundamental evaluation metrics in machine learning are:

- Precision
- Recall

But, their formal definitions can be a bit confusing.

In next 2 minutes I'll help you clearly understand them!

Let's go! 🚀 Image
Let's say there are 10 people in a Town.

2 of them have committed a crime, so in reality:

- 8 are innocent
- 2 are guilty

This is how it looks 👇 Image
Now, we hire a detective to catch the guilty parties!

The detective accuses 3 people of being guilty, while 7 are deemed innocent.

Out of the 3 accused, only 1 is actually guilty.

Out of the 7 predicted innocent, 1 is guilty in reality.

This is how the scenario looks so far👇 Image
Read 8 tweets
Akshay 🚀 Profile picture
Nov 6
Microsoft is offering FREE courses in following areas:

- AI
- IOT
- Data Science
- Machine Learning

A project-based pedagogy that allows you to learn while building! 🚀

Read More ...👇 Image
1️⃣ AI for beginners

A 12-week, 24-lesson curriculum all about Artificial Intelligence.

You'll learn about:
- Neural Nets
- Deep Learning
- Knowledge representation
- Genetic Algorithms & multi-agent systems

Check this out 👇
microsoft.github.io/AI-For-Beginne…
Image
2️⃣ IOT

Learn about IOT by doing project that cover the journey of food from farm to table.

This includes farming, logistics, manufacturing, retail and consumer - all popular industry areas for IoT devices.

Check this out 👇
microsoft.github.io/IoT-For-Beginn…
Image
Read 6 tweets
Akshay 🚀 Profile picture
Nov 1
Discover which model works best without any parameter tuning.

Introducing LazyPredict! 🚀

A Python library that enables you to train, test, and evaluate multiple ML models at once using just a few lines of code.

Supports both regression & classification! ✨

Check this out👇 Image
Here's an example for a regression task 👇 Image
You can find all the code 👇
github.com/shankarpandala…
Read 4 tweets
Akshay 🚀 Profile picture
Oct 28
Autoencoders are one of my favourite Neural Networks!

They are simple yet so powerful!

Today, We'll understand:

- What Autoencoders are❓
- How they are trained
- The applications of Autoencoders
- And how to implement them from scratch using PyTorch Lightning!⚡️

Let's go! 🚀 Image
Autoencoders have two main parts:

1️⃣ Encoder: Compresses the input into a dense representation (latent space)

2️⃣ Decoder: Reconstructs the input from this dense representation.

The idea is to make the reconstructed output as close to the original input as possible:👇 Image
Applications of Autoencoders:

- Dimensionality Reduction: Like PCA but cooler. 😎
- Anomaly Detection: If reconstruction error is high, something's fishy!
- Data Denoising: Clean noisy data by training on noise.

A glimpse on how a denoising autoencoder is trained:👇 Image
Read 10 tweets
Akshay 🚀 Profile picture
Oct 25
Pandas Vs NumPy!!

Pandas is built around column major format.

A subtle point that lot of us don't pay attention to & it leads to misuses of Pandas 🐼

Read more...👇 Image
Simply put, column-major format means, consecutive elements in a column are stored next to each other in memory.

Why you should care❓🤔

Ok, let's define a DataFrame👇 Image
Computers today are pretty good at processing sequential data than non-sequential data.

We claimed pandas is column-major❗️

So, we iterate over the df in 2 ways:
- First by columns
- Then by rows

Observe the difference in time taken 👇 Image
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

Send Email!

:(