You are on page 1of 7

45 Days Microsoft Placement Kit: https://youtu.be/8AKxbLFRatM 🛑 Microsoft Hyderabad Office Tour Vlog: https://youtu.

be/0TTSsDr1gP0 🛑
4 Months Placement Preparation Plan: https://youtu.be/KWPJZCFe3TA

Amazon DSA Revision Kit : https://github.com/KushalVijay/Amazon...

https://leetcode.com/discuss/intervie...

Leadership Principles Questions Kit: https://gist.github.com/by12380/3b327...

Amazon Online Test Prep Kit: https://github.com/NoobSolver/Amazon-... https://github.com/swolecoder/Amazon-...

Best Resources for Core Subjects: https://www.youtube.com/watch?v=tlTPO...

/////////////////////////////////////////////////////////////////////////////////////
Dp(45 problems):
https://lnkd.in/dDbVmWbC
Greedy(34 problems):
https://lnkd.in/d8hYvvub
Graphs(32 problems):
https://lnkd.in/dFPn4MF4
Backtracking(17 problems):
https://lnkd.in/dJEgYR26
Linkedlist(13 problems):
https://lnkd.in/d-XwqYY4
Bitmanipulation list(21 problems):
https://lnkd.in/dq7JpC9K
Hash table and map(46 problems):
https://lnkd.in/dnhQKmyB
Dsu or union find list(25 problems):
https://lnkd.in/dgrF-xuQ
Bridges and Articulation points(4 problems):
https://lnkd.in/dwdbPbtS
Djikstra Algorithm(13 problems):
https://lnkd.in/drv7e9Dp
Bellman Ford Algorithm(5 problems):
https://lnkd.in/ddwntGDX
Floyd Warshall Algorithm(6 problems):
https://lnkd.in/dTn-fXev
Topological sort(4 problems):
https://lnkd.in/dmXE9-pm
Sliding window(12 problems):
https://lnkd.in/dBbmrCeV
Trie(8 problems):
https://lnkd.in/dUPzXpDA
Monotonic queue and priority queue(13 problems):
https://lnkd.in/dsRQcTPv
Heaps(22 problems):
https://lnkd.in/duvBAgtS
Trees(Top 26):
https://lnkd.in/dgRNQb3V
Trees(Top 74):
https://lnkd.in/d7Si9q-S
Binary search(25 problems):
https://lnkd.in/dEH9cJDA
2pointers(30 problems):
https://lnkd.in/dt95PN6a
Must do easy questions:
https://lnkd.in/dZS5JTZn
Must do medium questions:
https://lnkd.in/d5RJ-pBr
60 questions to solve:
https://lnkd.in/dRfA7hxn
Blind curated 75:
https://lnkd.in/dmaT3zbV

Shubhankar Sir

Roadmap to Data Science and AI:


As the legend Andrew NG said, “If you don’t get it, you’ll get it later”

(This roadmap is made by Shubhankar Sharma.


Contact Details: shubhankar.code@gmail.com, +916266243366)

(This Roadmap is only intended for Students and Faculty Members of IIIT Bhopal,
kindly do not share it)

#NOTE: ML = Machine Learning; DL = Deep Learning; AI = Artificial Intelligence


DS = Data Science; NLP/U = Natural Language Processing / Understanding;
CV = Computer Vision

Stage 0: Learn Python: (Choose any one from 1,3 and 4 to


get started) (If you already know python and are confident enough, feel
free to skip)
1. Sentdex (Also known as pythonprogramming.net) - That’s how I got my hands on
Python
Intro to Python: https://pythonprogramming.net/introduction-learn-python-3-tutorials/
2. Intermediate Python: https://pythonprogramming.net/introduction-intermediate-python-
tutorial/
3. Krish Naik: This is a really good playlist - Python for Data Science - Krish is an ex Lead
Data Scientist at Panasonic https://www.youtube.com/playlist?
list=PLZoTAELRMXVNUL99R4bDlVYsncUNvwUBB
4. Dhaval Patel: Ex-Nvidia https://www.youtube.com/playlist?list=PLeo1K3hjS3uv5U-
Lmlnucd7gqF-3ehIh0

Stage 1: Overview and Exploration:

1. Machine Learning with Josh Gordan (Google ML Playlist)


This playlist is for getting an overview of machine learning.

2. After watching the above playlist, go through the following kaggle micro courses,
to get a deeper overview of Machine Learning and Deep Learning:
(Don’t worry, these courses will hardly take 5 hours per course at max)
a. Python: https://www.kaggle.com/learn/python
b. Pandas: https://www.kaggle.com/learn/intermediate-machine-learning
c. Intro to ML: https://www.kaggle.com/learn/intro-to-machine-learning
d. Intermediate ML: https://www.kaggle.com/learn/intermediate-machine-learning
e. Intro to DL: https://www.kaggle.com/learn/intro-to-deep-learning
(More Kaggle courses can be undertaken at will, but I’ll suggest to move to point)

(These to are good to learn to implement machine learning in basic structured


datasets - not much in depth, but quite good to learn to solve the basic problems,
one might find while using ML)

(Kaggle courses or micro courses are like a entry gate in the field of ML, you
start learning by doing)

3. Stanford Machine Learning (Andrew NG): Link - Week 1-3


(Boring, but a must to learn the most basic ML algo in DEPTH)
P.S. Try watching it at 1.25x - 1.5x ;p
This course is now discontinued in a favour of a complete specialisation:
https://www.coursera.org/specializations/machine-learning-introduction
4. Google Machine Learning Crash Course (Pretty good to get a comprehensive
overview of machine learning - what is the general method, goals:
https://developers.google.com/machine-learning/crash-course

After this point, you can either learn classical machine learning or deep learning
(but it is recommended to know basic classical / traditional machine learning, as
it gives better understanding of the field as whole).

Stage 2: Machine Learning:

5. Udacity Intro to ML: https://classroom.udacity.com/courses/ud120


(A really good course, even I’ll do it when I get time)

6. At this point I would recommend going out and trying standard practice problems
available at Analytics Vidhya (DataHack) and MachineHack.
https://datahack.analyticsvidhya.com/contest/all/
https://machinehack.com/hackathon
https://machinehack.com/practices

#Note: Not necessary to go through everything mentioned in point 5, but these


can prove really good to get hands on experience with all the skills learned till
Now (Image, text etc. problems can be skipped for now)

#You can go for either 7 or 8 or both (as you wish)

7. Stanford Machine Learning (Andrew NG): Link - Week 3-11


(Boring, but a must to learn the most basic ML algo in DEPTH)
P.S. Try watching it at 1.25x - 1.5x ;p

8. Krish Naik (Ex Lead Data Scientist at Panasonic): Krish Naik Complete ML

9. At this point I would recommend going out and trying standard practice problems
available at Analytics Vidhya (DataHack) and MachineHack.
https://datahack.analyticsvidhya.com/contest/all/
https://machinehack.com/hackathon
https://machinehack.com/practices

#Note: Not necessary to go through everything mentioned in point 8, but these


can prove really good to get hands on experience with all the skills learned till
now.

I know I am repeating this point, but yes it is important to go through this.

Stage 3: Deep Learning:

10. deeplearning.ai: Deep Learning Specialisation - Coursera: Link


(A must for building strong Deep Learning fundamentals)

11. Intro to TensorFlow for Deep Learning Link


(A must for getting hands on experience in deep learning, must after ‘8’)

12. At This point I would recommend going out and trying standard practice problems
available at Analytics Vidhya (DataHack) and MachineHack.
https://datahack.analyticsvidhya.com/contest/all/
https://machinehack.com/hackathon
https://machinehack.com/practices

#Note: Not necessary to go through everything mentioned in point 10, but these
can prove really good to get hands on experience with all the skills learned till
Now (Image, text etc. problems can be skipped for now)

I know I am repeating this point, but yes it is important to go through this.

#Note: PyTorch is a must learn for research:


https://www.udacity.com/course/deep-learning-pytorch--ud188

Some really Important books to go through:


1. Deep Learning Book is highly recommended
2. Elements of Statistical Learning is highly recommended
Link to all the books:
https://drive.google.com/drive/folders/1PEPD63Yl4yQ7LoRJ55pDkfdagvHLq02E?
usp=sharing

After this point, there is no specific path available. The learner has learnt enough to find
his / her own path. I’ll recommend everyone to have strong NLP foundations as it is
quite in demand.

I recommend going through advanced topics and other use cases.

1. NLP: Attention based transformers (Bert, GPT, T5, Megatrons, Roberta, Albert
etc.), Named Entity Recognition, Neural Machine Translation, Text
Summarisation, question answering and other sequence to sequence use cases.

2. Computer Vision: Object Detection, Image Segmentation, Image Captioning,


GANs, AutoEncoders / Variational AutoEncoders, Vision Transformers, Beit, etc.

Some resources which I refer to everytime I get stuck:


1. MIT Deep Learning - Lex Fridman: Link, Course Website
2. CS231n - Stanford University - Convolutional Neural Networks for Visual
Recognition: Link
3. CS224W - Stanford University - Machine Learning with Graphs: Link
4. CS224N - Natural Language Processing : Youtube playlist (2021 Course)
5. CS229 - Machine Learning - Andrew NG (2018): Youtube Playlist
6. CS230 - Deep Learning - Andrew NG(2018): Youtube Playlist

Keep an Eye on Stanford Online: https://www.youtube.com/user/stanfordonline/playlists


MIT OpenCourseWare: https://www.youtube.com/c/mitocw/featured

After this all the resources are available here:


https://docs.google.com/document/d/1oj7GVFy1-9XuK4Duq-aOkr0-
0FrZVeEjVWnFToyXWtw/edit?usp=sharing
MORE ON DATA ANALYST

Here are all the resources I mentioned in the video: 1. Learn Excel: https://excel-practice-online.com/

2. Learn SQL: https://www.w3schools.com/sql/

3. Learn PowerBI: https://www.datacamp.com/courses/intr...

4. Learn Python: https://www.learnpython.org/

5. Practice Projects at home: https://www.youtube.com/watch?v=r-uOL... & https://www.youtube.com/watch?v=qfyyn...

You might also like