NLP WITH MACHINE LEARNING AND DEEP LEARNING
-
Lecture 1 - Importance of NLP in Machine Learning (69:31)
-
Lecture 2 - Different preprocessing activities of text (49:23)
-
Lecture 3 - Feature extractions (42:18)
-
Lecture 4 - TFIDF (40:53)
-
Lecture 5 - Feature Extraction Using Python scikit learn (17:11)
-
Lecture 6 - Build model to classify sentiment analysis Using sklearn (26:21)
-
Lecture 7 - Sentiment Analysis Using RandomForest, Gaussian NB, SVM, and Selecting best model (45:42)
-
Lecture 8 - Comparision between ML model learning and Neural Network Learning Style (61:12)
-
Lecture 9 - How Simple Neural network works (34:16)
-
Lecture 10 - How Deep Neural Networks Work in Deep Learning (51:42)
-
Lecture 11 - Building and training Simple Artificial Neural networks for Sentiment Analysis (39:12)
-
Lecture 12 - Train Simple Neural networks (41:15)
-
Lecture 13 - Evaluating Neural Networks (41:09)
-
Lecture 14 - How to Convert Simple Neural Network to Deep Neural Network (48:44)
-
Lecture 15 - Train Deep Neural networks for Sentiment Classification (43:02)
-
Lecture 16 - Polynomial Sentiment Classification part 1 (49:01)
-
Lecture 17- Sentiment Classification implementation with Deep Learning using Python (58:05)
-
Lecture 18 - Gradient descent for predicting review or article score part 1 (56:40)
-
Lecture 19 - Gradient descent part 2 (52:39)
-
Lecture 20 - Transforming tfidf matrix as linear matrix and train using gradient descent (50:33)
-
Lecture 21 - Gradient Descent with TFIDF for Predicting Score (46:10)
-
Lecture 22 - Preprocessing of the text data (42:24)
-
Lecture 23 - Preprocessing of the text with python nltk (35:41)
-
Lecture 24 - Unsupervised learning on text data introduction (48:48)
-
Lecture 25 - Importance of heirarchical clustering (36:20)
-
Lecture 26 - K-means implementation with tfidf using sklearn (32:16)
