Deep Learning: Theory and Experiments

Notes

0. Course Roadmap

• Deep Learning
• Limits of Deep Learning

1. Background Materials

• Linear Algebra
• Probability
• Numerical Computation

2. Machine Learning Basics

• Concepts, Capacity, Estimators, Linear Regression
• MLE, Bayesian, Other ML Algorithms
• Stochastic Gradient Descent, etc

3. Deep Neural Networks

• Deep Feedforward Neural Networks, Cost, Output, Hidden Units
• Back Propagation

4. Regularization
5. Optimization
6. Convolutional Neural Networks
7. Embeddings
8. Recurrent Neural Networks, LSTM, GRU

Tensorflow (tf) Experiments

1. Hello World!
2. Linear Algebra
3. Matrix Decomposition
4. Probability Distributions using TensorBoard
5. Linear Regression by PseudoInverse
6. Linear Regression by Gradient Descent
7. Under Fitting in Linear Regression
8. Optimal Fitting in Linear Regression
9. Over Fitting in Linear Regression
10. Nearest Neighbor
11. Principal Component Analysis
12. Logical Ops by a 2-layer NN (MSE)
13. Logical Ops by a 2-layer NN (Cross Entropy)
14. NotMNIST Deep Feedforward Network: Code for NN and Code for Pickle
15. NotMNIST CNN
16. word2vec
17. Word Prediction/Story Generation using LSTM. Belling the Cat by Aesop Sample Text Story

Keras on Tensorflow Experiments

1. NotMNIST Deep Feedforward Network
2. NotMNIST CNN
3. DCGAN on MNIST