00:04 Top 5 recommended ML projects to enhance your portfolio 00:35 Focus on practical projects over unique ideas. 01:03 Build a sentiment analysis model 01:35 Work with text-based datasets effectively 02:07 Build a PDF chat application using rag technique 02:39 Implement a Convolutional Neural Network from scratch 03:10 Building a language model from scratch using library like pytorch 03:40 Introduction to the beginner blueprint
Thanks, after watching this I feel great , coz 4 out of 5 you mentioned are already in my portfolio. I would like to add a few more like time series forecasting or anomaly detection, these are critical too imo
My ML programming problems are hosted on my colleague Navdeep's code sandbox! Here's the link to the platform: neetcode.io/practice?subpage=practice&tab=coreSkills&topic=Machine%20Learning
For each of these projects, I've seen multiple hiring managers on LinkedIn recommend them! As for how common these projects are, IMO the more important thing is being able to explain how you built the entire project in an interview setting, as this would display a deep understanding.
Heyy...ik web dev...so should I now start with ML or do I have to have to do data analysis first (tools like power bi and stuff)...can u guide me how I can start?
This one is up for debate. Projects like fine tuning and RAG provide more abstraction of the actual model, so they're easier to get started with, though you won't be exposed to the underlying math. On the other hand, projects like implementing a language model expose you to much more of the underlying details, but are intense and require a strong understanding of the fundamentals (i.e. basic Neural Networks). One solid option is Sentiment Analysis -> Language Model -> Fine Tuning -> RAG.
LLM Liftoff: bit.ly/406RhQC
00:04 Top 5 recommended ML projects to enhance your portfolio
00:35 Focus on practical projects over unique ideas.
01:03 Build a sentiment analysis model
01:35 Work with text-based datasets effectively
02:07 Build a PDF chat application using rag technique
02:39 Implement a Convolutional Neural Network from scratch
03:10 Building a language model from scratch using library like pytorch
03:40 Introduction to the beginner blueprint
Thanks, after watching this I feel great , coz 4 out of 5 you mentioned are already in my portfolio. I would like to add a few more like time series forecasting or anomaly detection, these are critical too imo
what that portfolio ! like can i see to make mine
Do you actually get interviews with your portfolio?
@@al-manasama8370 I haven't started applying yet, just finished with that llm fine tuning one
That's awesome man! And yeah, those projects are definitely useful as well.
The point you missed is that to build an LLM, you need GPU
done in 15 hours
0:58 Which website is that?
My ML programming problems are hosted on my colleague Navdeep's code sandbox! Here's the link to the platform: neetcode.io/practice?subpage=practice&tab=coreSkills&topic=Machine%20Learning
How many hiring managers you ask about this? Are those projects become common projects for every industry?
For each of these projects, I've seen multiple hiring managers on LinkedIn recommend them!
As for how common these projects are, IMO the more important thing is being able to explain how you built the entire project in an interview setting, as this would display a deep understanding.
Heyy...ik web dev...so should I now start with ML or do I have to have to do data analysis first (tools like power bi and stuff)...can u guide me how I can start?
really great projects..but somewhere i feel integrating an llm to a modern day usecase is much interesting..any thoughts on this
Would you reccomend doing these in this order?
This one is up for debate. Projects like fine tuning and RAG provide more abstraction of the actual model, so they're easier to get started with, though you won't be exposed to the underlying math. On the other hand, projects like implementing a language model expose you to much more of the underlying details, but are intense and require a strong understanding of the fundamentals (i.e. basic Neural Networks).
One solid option is Sentiment Analysis -> Language Model -> Fine Tuning -> RAG.
Wanted some personal mentorship, if possible would you like to offer some mentorship?
Nice
🙏