Machine Learning in 5 hrs [Urdu/Hindi]
#machinelearning #neuralnetworks #convolutionalneuralnetwork
I have tried to sum up complete Machine Learning course in 5 hours in this video. In addition to topics covered in original famous Andrew Ng's Coursera course (Linear and Logistic Regression, Regularization, Neural networks, SVMs, Clustering, PCA, Recommender systems, Decision Trees) we also covered CNNs (Convolutional Neural Networks) which is part of Deep learning specialization course.
A 30 lectures course becomes too big a commitment for most people. Now you can go through this shorter course instead of and fall back on specific videos if some topic is unclear, the link to course playlist is: • Course Intro, Machine Learning Lec 1/30 [U...
Course Material (Slides/Assignments): https://tinyurl.com/ml-renzym
Python tutorial (for doing Assignments): • Python/Numpy/Jupyter in 2 hrs [Urdu/Hindi]
SUBSCRIBE! Also Enable Notifications by clicking bell button on channel page
https://www.youtube.com/c/RenzymEduca...
Topics timeline:
(0:00) Machine learning intro
(1:58) Intro: Supervised Learning
(5:02) Intro: Unsupervised learning
(6:33) Linear regression: Model representation
(16:24) Linear regression: Cost function
(23:47) Gradient descent
(32:57) Briefest overview of matrices
(35:07) Multiple features
(42:06) Feature scaling, Mean normalization
(46:53) Learning rate
(49:27) Polynomial regression
(53:23) Normal equation
(59:22) Logistic regression/Classification
(1:14:30) Multi-class classification
(1:17:20) Regularization: Problem of overfitting
(1:26:33) Non-linear hypothesis
(1:30:22) Neurons and Model representation
(1:44:19) Multi-classclassification
(1:45:43) Neural network Cost function
(1:47:36) Back propagation
(1:59:31) Gradient checking, random initialization
(2:04:48) Machine learning advice: Deciding what to do next
(2:06:51) Evaluating a hypothsis
(2:08:56) Model selection and training/validation/test sets
(2:11:00) Diagnosing bias vs variance, Regulrization
(2:14:51) Learning curves
(2:18:31) Spam classification example
(2:23:35) Error Analysis
(2:29:22) Error metric for skewed classes, precision, recall, F-score
(2:34:31) Data for machine learning
(2:36:15) Fashion MNIST Tensor Flow example
(2:40:14) SVM - Support vector machines
(2:44:20) SVM: Maths behind large margin classifier
(2:51:34) SVM: Kernels
(3:04:11) Clustering
(3:10:50) Dimensionality reduction: Principale Component Analysis PCA
(3:26:22) Anomaly Detection
(3:46:30) Recommender Systems
(3:58:49) Large datasets, Stochastic/Mini-batch gradient descent, Map-reduce
(4:07:20) OCR example, Sliding window, Ceiling analysis
(4:17:49) Decision trees, Tree ensembles, Random Forests
(4:36:09) Convolutional Neural Networks CNNs
(4:45:20) CNN case studeies: LeNet-5, AlexNet, VGG-16, Resnet, Inception
(4:52:40) Object Detection and Yolo quick overview
(4:57:24) Face recognition/verification,