CS230: Deep Learning
A distilled compilation of my notes for Stanford's CS230: Deep Learning.
Notes
Introduction to Deep Learning
what is a neural network; logistic regression; python and vectorization; examples of deep learning projects
Neural Networks
deep learning intuition; neural network basics; shallow neural networks; deep neural networks
Optimizing and Structuring Neural Networks
full-cycle of a deep learning project; Regularization; optimization; hyperparameter tuning; batchnorm
Applied Deep Learning
orthogonalization; comparing to human-level performance; error analysis; mismatched training and dev set; learning from multiple tasks
Adversarial Attacks and Defenses
attacking networks with adversarial examples; types of attacks; adversarial defenses
Convolutional Neural Networks
edge detection; padding; strided convolutions; cross-correlation vs. convolution; pooling layers
Object Detection Algorithms
object detection and localization; landmark detection; intersection over union (IoU); non-max suppression; anchor boxes; YOLO
Sequence Models
recurrent neural networks; gated recurrent units; long short-term memory
Generative Adversarial Networks (GANs)
training GANs; GAN applications
Interpretability of Neural Networks
saliency maps; visualizing neural networks; deconvolution and its applications
Deep Reinforcement Learning
markov decision process; bellman equation; deep Q-learning
Course Info
Course description:
- Deep Learning is one of the most highly sought after skills in AI. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects.
- You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more.
Credits
The in-line diagrams are taken from the CS230 lecture slides, unless specified otherwise. Reproduced with permission.
Citation
If you found our work useful, please cite it as:
@misc{Chadha2020DistilledNotesCS230,
author = {Chadha, Aman},
title = {Distilled Notes for Stanford CS230: Deep Learning},
howpublished = {\url{https://www.aman.ai}},
year = {2020},
note = {Accessed: 2020-09-01},
url = {www.aman.ai}
}
A. Chadha, Distilled Notes for Stanford CS230: Deep Learning, https://www.aman.ai, 2020, Accessed: Sept 1 2020.