Published videos

• Amazon Fine Food Reviews | NLP Preprocessing & EDA in Python (Coding)

  In this video, we begin the coding part of our Natural Language Processing (NLP) journey using the Amazon Fine Food Reviews dataset. You'll learn how to prepare raw text data before applying machine learning models. This includes downloading the dataset, performing Exploratory Data Analysis (EDA), cleaning the text, removing stop words, and applying stemming. In this video, you'll learn: • Downloading the Amazon Fine Food Reviews dataset • Loading and exploring the dataset using Pandas • Performing Exploratory Data Analysis (EDA) • Understanding the structure and distribution of the data • Text cleaning and preprocessing • Removing stop words • Applying stemming using NLTK • Preparing clean text for feature engineering This is the first coding video in the NLP series. In the next video, we'll implement Bag of Words (BoW) to convert the preprocessed text into numerical features that machine learning models can understand. 📚 Perfect for: • NLP Beginners • Machine Learning Students • Data Science Enthusiasts • Python Developers • AI Learners • Interview Preparation

• Average Word2Vec & TF-IDF Weighted Word2Vec Explained

  In this video, you'll learn Average Word2Vec (AvgW2Vec) and TF-IDF Weighted Word2Vec—two simple yet powerful techniques for converting an entire document or sentence into a single vector representation. After learning Word2Vec, the next question is: How do we represent a complete sentence or document when Word2Vec only gives vectors for individual words? In this video, we'll build intuition behind: • What is Average Word2Vec (AvgW2Vec)? • How to generate document embeddings using Word2Vec • Why simple averaging has limitations • What is TF-IDF Weighted Word2Vec? • Why TF-IDF weighting often produces better document representations • Real-world examples and intuitive explanations This video focuses on conceptual understanding without diving into complex mathematics. In later videos, we'll implement these techniques in Python and continue building toward modern NLP and Generative AI concepts. 📚 Perfect for: • NLP Beginners • Machine Learning Students • Data Science Enthusiasts • AI Learners • Interview Preparation #AverageWord2Vec #Word2Vec #TFIDF #NLP #MachineLearning #DeepLearning #ArtificialIntelligence #DataScience #Python #LLM #GenerativeAI #ComputerScience

• Bag of words | featurization | preprocessing | Machine Learning part 2

  Here we will learn about the bag of words featurization technique available in machine learning which just count the number of words in each reviews for each feature. #bagofwords #featurization #machine_learning

• Bag of Words Space Complexity Optimization | Sparse Matrix vs Dictionary (Best)

  In this video, you'll learn how to optimize the space complexity of the Bag of Words (BoW) representation in Natural Language Processing (NLP). Instead of storing a large N × M sparse matrix, we'll see how using a dictionary-based sparse representation significantly reduces memory usage from O(N × M) to O(3K), where K is the number of non-zero entries. 📌 In this video: What is the Bag of Words model? Why the BoW matrix is sparse Space complexity of the traditional matrix representation Dictionary-based sparse representation How memory usage reduces from O(N × M) to O(3K) Step-by-step example Why sparse representations are preferred in real-world NLP systems This video is perfect for students preparing for: Data Structures & Algorithms (DSA) Machine Learning Natural Language Processing (NLP) AI Interviews College Exams Technical Interviews

• Classification vs Regression in Machine Learning | Explained with Simple Examples

  Classification vs Regression — two of the most fundamental concepts in Machine Learning. In this video, we understand the difference between Classification and Regression with simple, intuitive examples. You’ll learn when to use each type of supervised learning problem and how their predictions differ. Topics covered: • What is Classification? • What is Regression? • Classification vs Regression • Real-world examples • How to identify whether a problem is classification or regression • Understanding categorical vs continuous outputs This video is useful for beginners learning Machine Learning, Data Science, and AI fundamentals.

• Featurization | Preprocessing | Machine Learning | part 1

  here we will learn about intro to the featurization. featurization is the steps in machine learning that comes under the preprocessing where we convert the raw data into numerical form. #featurization #preprocessing #machine_learning

• Stopwords | stemming | lemmatization | text preprocessing | machine learning part 3

  Here we will learn about the three terms used in the text preprocessing i.e. stop words, stemming and lemmatization. We will see the steps evolved in the text preprocessing. #stopwords #stemming #lemmatization #textpreprocessing #machinelearning

• TF-IDF Explained Simply | Complete Beginner's Guide with Examples

  Learn TF-IDF (Term Frequency–Inverse Document Frequency) from scratch in this beginner-friendly tutorial. In this video, you'll understand what TF-IDF is, why it is used in Natural Language Processing (NLP), how the TF-IDF formula works, and solve numerical examples step by step. Topics Covered: • What is TF-IDF? • What is Term Frequency (TF)? • What is Inverse Document Frequency (IDF)? • TF-IDF Formula Explained • Step-by-Step Numerical Example • Applications of TF-IDF in Machine Learning and NLP This video is perfect for students, beginners, interview preparation, and anyone learning Machine Learning, Natural Language Processing (NLP), Data Science, Artificial Intelligence, and Information Retrieval. If you found this video helpful, please Like, Share, and Subscribe for more AI, Machine Learning, and Computer Science tutorials. #TFIDF #MachineLearning #NLP #ArtificialIntelligence #DataScience #Python #InformationRetrieval #TextMining #AITutorial #ComputerScience

• unigram | bigram | ngram | machine learning tutorial

  Welcome to this machine-learning tutorial where we dive into the concepts of unigrams, bigrams, and n-grams in natural language processing (NLP). In this video, you'll discover: What unigrams, bigrams, and n-grams are, and how they work. Why ngram over unigram? 🔔 Don't forget to like, subscribe, and hit the notification bell for more machine learning tutorials! #Unigram #Bigram #Ngram #MachineLearning #NLP #TextAnalysis

• Word2Vec Made Simple | Intuition & Examples

  In this video, you'll learn *Word2Vec* through simple intuition and real-world examples—without diving into complex mathematics or deep learning. The goal is to build a strong conceptual understanding of how Word2Vec converts words into meaningful vector representations and why it became one of the most influential techniques in Natural Language Processing (NLP). By the end of this video, you'll understand: What Word2Vec is Why traditional word representations are limited How Word2Vec captures semantic meaning Why similar words end up close together in vector space Real-world examples to build intuition How Word2Vec laid the foundation for modern NLP models This video is part of my *Natural Language Processing (NLP)* series. In future videos, we'll implement Word2Vec from scratch and explore the underlying deep learning concepts such as *CBOW (Continuous Bag of Words)* and **Skip-gram**. 📚 Perfect for: Beginners in NLP Machine Learning students Deep Learning enthusiasts Interview preparation AI and Data Science learners #Word2Vec #NLP #MachineLearning #DeepLearning #ArtificialIntelligence #WordEmbeddings #Python #DataScience #LLM #GenerativeAI #ComputerScience