🦝 Week 1: NLP Intro Pack and Sentiments 👾 Day 1: Overview First of all, check out this amazing playlist by TensorFlow to get a crisp idea of what we are going to do this week. It's packed with insightful videos that will lay a solid foundation for your NLP journey! YouTube 👾 Day 2: Kickstarting with Text Preprocessing, Normalization, Regular Expressions, and Edit Distance a. Text Preprocessing: The Foundation of NLP Imagine trying to read a messy, smudged book – not fun, right? Text preprocessing is like cleaning up that book, making it crisp and readable. It transforms chaotic, noisy text into a tidy format that's ready for analysis. This process is crucial because cleaner data leads to better NLP model performance!

Welcome to the Computer Vision Roadmap by Programming Club IITK, wherein we'll be building right from the preliminary techniques of Image Processing and thereafter largely cover the intersection of Machine Learning and Image Processing. We're expecting that you're here after completing the Machine Learning Roadmap, which covers the basics of Machine Learning, Neural Networks, Pipelines and other preliminary concepts; so in this roadmap, we assume that the explorer has that knowledge and we pick up from there. Even if you have explored Machine Learning independently, we strongly recommend you to go through the ML Roadmap once before starting this. Although all topics are not prerequisite, but most of them are. Also do remember, in case you face any issues, the coordies and secies @Pclub are happy to help. But a thorough research amongst the resources provided before asking your queries is expected :) Computer Vision is all about giving 1s and 0s the ability to see. Let's get started with Computer Vision 👾 https://www.ibm.com/topics/computer-vision

Welcome to the Machine Learning Roadmap by Programming Club IITK, where we will be giving you a holistic and hands-on introduction to the world of Machine Learning. The roadmap is divided into 8 weeks of content and each week progressively builds upon a new concept. The roadmap includes a lot of material and assignments, which while not trivial are definitely doable given the right amount of motivation and determination. Also do remember, in case you face any issues, the coordies and secies @Pclub are happy to help. But a thorough research amongst the resources provided before asking your queries is expected :) Before beginning, understand that the week allocation and order of topics covered is just a recommended order (Highly Recommended tho). For the first few weeks, we'd strongly recommend you to follow the order, since mathematics and basic foundations are quintessential for understanding working on any kind of model. Post that you can prolly play around with the order, take a few detours and come back. To explain how to do this in an a coherent fashion, we'll now give a run-through of the map. Week 1 is basic python and libraries and week 2 covers basic mathematics, and the core fundamentals. Week 3 covers techniques important for improving ML pipelines. Follow these 3 weeks in order. 4th Week covers some of the most important algorithms, but they are not a prerequisite for week 4 (Intro to Neural Networks), so if you are too impatient to jump on the Neural Network and Deep Learning wagon, you can move to week 5 without completing week 4 (We'd recommend going the principled way tho). Moreover, week 7 (Unsupervised Learning) is pretty independent of all the weeks (except the first 3 weeks), so if you wish to explore Unsupervised Learning early, you can do that anytime. Week 6 covers some important topics like Optimization Algorithms, Feature Selection and Boosting Algorithms. You can go ahead with the first 2 subtopics without week 5, but Boosting Algorithms will require a strong understanding of Decision Trees so for that you'd have to go back to week 4. You can also cover Boosting Algorithms just after Ensemble Methods (Week 4, Day 4) if you're having fun learning about Decision Trees and wish to go deeper (ik, this was a pathetic attempt at cracking tree pun; just bear with for this not-so-short journey). Coming to Python Libraries, PyTorch and Tensorflow are the most famous for Deep Learning, and ScikitLearn for ML in general. You'd learn sklearn as and when you progress the weeks, but after completing week 5 and the first 5 days of week 6, you'd have to pick one framework from PyTorch or Tensorflow. You can chose any one of them and getting a hang of one will also make it easier to understand the other. Once you're done with one framework, you can start building projects, learning the other framework, or exploring other specialized domains like CV or NLP.

Week 1: Getting Ready for NLP & Preprocessing 📅 DAY 1: Getting an overview First of all, check out this amazing playlist by TensorFlow to get a crisp idea of what we are going to do this week. It's packed with insightful videos that will lay a solid foundation for your NLP journey! YouTube 📅 DAY 2: Kickstarting with Text Preprocessing, Normalization, Regular Expressions, and Edit Distance a. Text Preprocessing: The Foundation of NLP Imagine trying to read a messy, smudged book – not fun, right? Text preprocessing is like cleaning up that book, making it crisp and readable. It transforms chaotic, noisy text into a tidy format that's ready for analysis. This process is crucial because cleaner data leads to better NLP model performance!

Week 1: Mastering Clustering and Unsupervised Machine Learning 📅 DAY 1: Introduction to Unsupervised Learning and Clustering a. Unsupervised Learning: Discovering Hidden Patterns Unsupervised learning is a type of machine learning that looks for previously undetected patterns in a dataset with no pre-existing labels and with a minimum of human supervision. Unlike supervised learning, there are no predefined target variables. The goal is to identify patterns, groupings, or structures within the data. 🔍 Learn More:Get started with this comprehensive overview on unsupervised learning. b. Clustering: Grouping Data Intelligently Clustering is a fundamental unsupervised learning technique used to group similar data points together. It aims to divide the data into clusters, where points in the same cluster are more similar to each other than to those in other clusters.

🚀 Feature Selection: Supercharge Your Models Feature selection is a crucial process that helps in choosing the most important features from your dataset, reducing the feature space while preserving the essential information. This not only speeds up your algorithms by reducing dimensionality but also enhances prediction accuracy. Imagine dealing with a dataset having hundreds of columns – without feature selection, it would be a computational nightmare! Check out this dataset on Kaggle. It has about 200 columns, and handling computations on such a large scale can be challenging. Feature selection plays a vital role here, and you might encounter even larger datasets in real-world scenarios. Why is Feature Selection Important? Speed: Faster computations and quicker model training. Accuracy: Improved model predictions by eliminating noise and redundant data. Simplicity: Easier to interpret and understand the model.