CS231n：

Bayesian Hyperparameter Optimization is a whole area of research devoted to coming up with algorithms that try to more efficiently navigate the space of hyperparameters. The core idea is to appropriately balance the exploration - exploitation trade-off when querying the performance at different hyperparameters. Multiple libraries have been developed based on these models as well, among some of the better known ones are Spearmint, SMAC, and Hyperopt. However, in practical settings with ConvNets it is still relatively difficult to beat random search in a carefully-chosen intervals. See some additional from-the-trenches discussion here.

---

CS231n Convolutional Neural Networks for Visual Recognition

These notes accompany the Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition. 
For questions/concerns/bug reports contact Justin Johnson regarding the assignments, or contact Andrej Karpathy regarding the course notes. You can also submit a pull request directly to our git repo. 
We encourage the use of the hypothes.is extension to annote comments and discuss these notes inline.

Spring 2019 Assignments

Assignment #1: Image Classification, kNN, SVM, Softmax, Neural Network

Assignment #2: Fully-Connected Nets, Batch Normalization, Dropout, Convolutional Nets

Assignment #3: Image Captioning with Vanilla RNNs, Image Captioning with LSTMs, Network Visualization, Style Transfer, Generative Adversarial Networks

Module 0: Preparation

Setup Instructions

Python / Numpy Tutorial

IPython Notebook Tutorial

Google Cloud Tutorial

AWS Tutorial

Module 1: Neural Networks

Image Classification: Data-driven Approach, k-Nearest Neighbor, train/val/test splits

L1/L2 distances, hyperparameter search, cross-validation

Linear classification: Support Vector Machine, Softmax

parameteric approach, bias trick, hinge loss, cross-entropy loss, L2 regularization, web demo

Optimization: Stochastic Gradient Descent

optimization landscapes, local search, learning rate, analytic/numerical gradient

Backpropagation, Intuitions

chain rule interpretation, real-valued circuits, patterns in gradient flow

Neural Networks Part 1: Setting up the Architecture

model of a biological neuron, activation functions, neural net architecture, representational power

Neural Networks Part 2: Setting up the Data and the Loss

preprocessing, weight initialization, batch normalization, regularization (L2/dropout), loss functions

Neural Networks Part 3: Learning and Evaluation

gradient checks, sanity checks, babysitting the learning process, momentum (+nesterov), second-order methods, Adagrad/RMSprop, hyperparameter optimization, model ensembles

Putting it together: Minimal Neural Network Case Study

minimal 2D toy data example

Module 2: Convolutional Neural Networks

Convolutional Neural Networks: Architectures, Convolution / Pooling Layers

layers, spatial arrangement, layer patterns, layer sizing patterns, AlexNet/ZFNet/VGGNet case studies, computational considerations

Understanding and Visualizing Convolutional Neural Networks

tSNE embeddings, deconvnets, data gradients, fooling ConvNets, human comparisons

Transfer Learning and Fine-tuning Convolutional Neural Networks

• cs231n
• cs231n
• karpathy@cs.stanford.edu