Stanford Open Learning Initiative Unless otherwise noted this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

Chapter	Chapter	Chapter
1. Exploratory Data Analysis and Statistics	2. Frequency Distributions	3. Numerical Measures
4. Measures of Spread	5. Standard Deviation	Ex-1. Exploring Variables in a Dataset
6. Examining Relationships	7. Linear Relationships	8. Regression
9. Causation	Ex-2. Building A Two-Way Table	10. Producing Data
11. Designing Studies	12. Sample Surveys	Ex-3. Exploring Simple Random Samples
13. Blind and Double-Blind Experiments	Ex-4. Creating Similar Treatment Groups	14. Introduction to Probability
15. Relative frequency	16. Probability Rules	17. General Addition Rule
18. Conditional Probability	19. Independence Check	20. Probability Trees
21. Random Variables	22. Mean and Variance	23. Binomial Random Variables
Ex-5. Calculating Probabilities for Binomial Random Variables	24. Normal Random Variables	25. Normal Approximation to the Binomial
Ex-6. Using the Normal Distribution	26. Inference	27. Point Estimation
28. Confidence Intervals	29. Hypothesis Testing	30. Population Proportion p: z-test
Ex-8. Carrying Out the z-test	Ex-9. Examining the Conditions for the z-test	Ex-10. Examining the Conditions for the z-test
31. Population Proportion p: Effect of Sample Size	32. Population Mean: Confidence Intervals	Ex-7. Calculating Confidence Intervals
33. Inference for Relationships	34. Two Independent Samples	Ex-11. Checking Conditions for the Two-Sample t-test
35. Matched Pairs	36. ANOVA	37. Chi-Square Test
Ex-12. Testing for a Linear Relationship

Chapter	Chapter	Chapter
1. Introduction to Machine Learning	2. Linear Algebra	3. Linear Regression with One Variable
Ex-1. Octave Tutorial : Basic Operations	4. Gradient Descent	5. Linear regression with multiple variable
Ex-2. Linear Regression	6. Gradient Descent For Multiple Variables	Ex-3. Linear Regression with multiple variables
7. Logistic regression	8. Cost function	Ex-4. Logistic Regression
9. Problem of Overfitting	Ex-5. Regularized Logistic Regression	10. Neural Networks
Ex-7. Neural Networks Learning	11. Cost Function	12. Advice for Applying Machine Learning
13. Diagnosing Bias vs. Variance	Ex-8. Regularized Linear Regression	14. Prioritizing What to Work On
15. Support vector machines	16. SVM Large margin intuition	17. Large margin classification mathematics
18. Adapting SVM to non-linear classifiers	Ex-9. Support Vector Machines	19. Unsupervised learning
20. K Means Algorithm	Ex-10. K-means Clustering	21. Dimension reduction
Ex-11. Principal Component Analysis	22. Anomaly Detection	Ex-12. Anomaly Detection Systems
23. Recommender systems	Ex-13. Recommender Systems	24. Learning With Large Datasets
Machine Learning - Lab Exercises Solutions	25. Canadian Institute for Cybersecurity - malware dataset	26. Android system calls malware dataset

Chapter	Chapter	Chapter
1. Deep Learning	2. Supervised Learning with Neural Networks	3. Why Deep Learning is taking off ?
Quiz 1: Introduction to deep learning	4. Neural Network Basics	5. Logistic regression
6. Deep Learning course notations	7. Logistic Regression: Cost Function	8. Logistic Regression: Gradient Descent
9. Basics of Neural Network Programming - Derivatives	10. Computation graph	11. Logistic Regression Gradient Descent
12. Introduction to Vectorization	13. Vectorizing Logistic Regression	14. Broadcasting in Python
Quiz 2: Neural Network Basics	Introductory Video	PE-1. Python Basics With Numpy
PE-2. Logistic Regression with a Neural Network mindset	15. Neural Networks Overview	16. Computing a Neural Network's Output - Second Layer
Python - Simple Neural network in Keras	Python - Initializers for bias, kernel in Keras	Python - Optimizations in Keras
Python - Datasets in Keras	Python - Data augmentation in Keras	Python - Dense Layers in Keras
Python - Activations in Keras	Python - Metrics in Keras	Python - Callbacks in Keras
Python - Loss functions in Keras	Python - Using ImageNet in Keras - I	Python - Using ImageNet in Keras - II
17. Activation functions	18. Gradient descent for Neural Networks	Quiz 3: Shallow Neural Networks
PE-3. Planar data classification with one hidden layer	19. Deep L-layer neural network	20. Getting your matrix dimensions right
21. Building blocks of deep neural networks	22. Forward and Backward Propagation	Quiz 4: Key concepts on Deep Neural Networks
PE-4 Building your Deep Neural Network Step by Step	PE-5. Deep Neural Network Application	Python: Multilabel classification
Building autoencoders	Tensorflow: Time series	Tensorflow: Time series Multioutput
Imbalanced datasets	Sentiment analysis with trax

Chapter	Chapter	Chapter
1. Setting up your Machine Learning Application	2. Bias / Variance	3. Basic Recipe for Machine Learning
4. Regularizing your neural network	5. Why regularization reduces overfitting?	6. Dropout Regularization
7. Understanding Dropout	8. Other regularization methods	9. Normalizing inputs
10. Vanishing / Exploding gradients	11. Weight Initialization for Deep Networks	12. Numerical approximation of gradients
Quiz 1: Practical aspects of deep learning	Introductory Video	PE-1. Improving Deep Neural Networks
PE-2. Gradient Checking	PE-3. Regularization	13. Need for Optimization Techniques
14. Understanding mini-batch gradient descent	15. Exponentially weighted averages	16. Understanding exponentially weighted averages
17. Bias correction in exponentially weighted averages	18. Gradient descent with momentum	19. RMSProp - Root Mean Square Prop
20. Adam optimization algorithm	21. Learning rate decay	Quiz 2: Optimization algorithms
PE-4. Optimization	22. Tuning process	23. Using an appropriate scale to pick hyperparameters
24. Hyperparameters tuning in practice: Pandas vs. Caviar	25. Normalizing activations in a network	26. Softmax Regression
Quiz 3: Hyperparameter tuning, Batch Normalization, Programming Frameworks	PE-5. Tensorflow

Chapter	Chapter	Chapter
1. Introduction to ML Strategy - Why ML Strategy	2. Single number evaluation metric	3. Satisficing and Optimizing metric
4. Train/dev/test distributions	5. Size of the dev and test sets	6. When to change dev/test sets and metrics
7. Comparing to human-level performance	8. Avoidable bias	9. Understanding human-level performance
10. Surpassing human-level performance	Quiz 1: Bird Recognition system (Case study)	11. Carrying out error analysis
12. Cleaning up incorrectly labeled data	13. Build your first system quickly, then iterate	14. Training and testing on different distributions
15. Transfer learning	16. Multi-task learning	17. End-to-end deep learning
Quiz 2: Autonomous driving (Case study)

Chapter	Chapter	Chapter
1. Computer Vision	2. Edge Detection Example	3. More Edge Detection
4. Padding	5. Strided Convolutions	6. Convolutions Over Volume
7. One Layer of a Convolutional Network	8. Simple Convolutional Network Example	9. Pooling Layers
10. CNN Example	11. Why Convolutions?	Quiz 1: Basics of ConvNet
Introductory Video	PE-1. Convolutional Neural Networks: Step by Step	12. Deep convolutional models: case studies
Keras: Toxic_Comments_Classification using 1D CNN	Keras: Text Processing by Google ML	Keras: Text Processing by Google ML-2
Keras: Understanding 1D Convolution Neural Network	Keras: Time Sequences	Keras: Implementing a 1D CNN
Keras: Sentiment Analysis	Keras: Time Series Forecasting	Tensorflow: 1DCNN Time Series Forecasting
13. Classic Networks - LeNet-5	14. ResNets	15. Networks in Networks and 1x1 Convolutions
16. Practical advice for using ConvNets - Using Open-Source Implementation	Quiz 2: Deep Convolutional models	PE-2. Convolutional Neural Networks: Application
Keras: Conv2D	Keras: 2D CNN for MNIST	Keras: 2D CNN for Arabic alphabets
Keras: 2D CNN for Fashion MNIST	Keras: 2D CNN for Flower recognition	Keras: 2D CNN for Adverserial Network
Keras: Transfer learning	Keras: Using bottleneck features	Keras: Using Fine Tuning
Keras: Resnet for EmotionAI	Keras: Facial expression detection	Keras: Classify Radio Signals
Keras: Transfer learning for Food classification	Keras: Traffic sign classification
17. Detection algorithms - Object Localization	18. Detection algorithms - Landmark Detection	19. Detection algorithms - Object Detection
20. Convolutional Implementation of Sliding Windows	21. Bounding Box Predictions	22. Anchor Boxes
23. Region Proposals	Quiz 3: Detection algorithms	PE-3. Keras tutorial - the Happy House
24. What is face recognition?	25. Siamese Network	26. Triplet Loss
Siamese networks in Python
27. Face Verification and Binary Classification	28. What is neural style transfer?	29. Cost Function
Keras: Object Detection YOLOv3	Object Detection YOLOv5	Keras: Neural Style Transfer
Keras: Video object Detection YOLOv3	Keras: Conv2d Autoencoders
30. 1D and 3D Generalizations	Quiz 4: Special Applications	PE-4. Residual Networks
PE-5. Autonomous driving - Car detection

Chapter	Chapter	Chapter
1. Why sequence models	2. Recurrent Neural Network Model	3. Backpropagation through time
4. Different types of RNNs	5. Language model and sequence generation	6. Sampling novel sequences
7. Vanishing gradients with RNNs	8. Gated Recurrent Unit (GRU)	9. Long Short Term Memory (LSTM)
10. Bidirectional RNN	11. Deep RNNs	12. Word Representation
QUIZ: Recurrent neural networks
13. Using word embeddings	14. Properties of word embeddings	15. Embedding matrix
16. Learning word embeddings	17. Negative Sampling	18. GloVe word vectors
QUIZ: Word embeddings
Python: What is NLP ?	Python: Tokenize words	Python: Building a NLP pipeline
19. Sequence-to-sequence models	20 Beam Search	21. Attention Model Intuition
22. Speech recognition	Naive bayes model	Part of Speech-Markov models-I
Part of Speech-Markov models-I	Continuous bag of words model
QUIZ: Sequence to sequence models
Python for RNN	RNN for Stock Price Prediction	RNN for Simple Addition
LSTM for Named Entity Recognition	LSTM for English to French Translation
LSTM for Fake News Detection	LSTM for Anamoly Detection in Time series	Multistep Time series in CNN RNN

Chapter	Chapter	Chapter
1. Basic Graph Convolutional Network	2. Graph Convolutional Network on CORA Data	3. Graph Convolutional Network on Bitcoin Data