Deep learning has been getting lots of attention from many different fields including business/finance, image handling and even science simulation. 2-Day Deep learning course in Summer School 2021 will be a good foundation course for who wants to actually program it. The course will proceed with presentation and live demonstration using Google Colab.
Day 1 will cover Multivariable linear regression and MNIST image classification using linear and Multi-Layer Perceptron (MLP) including some techniques to avoid overfitting. Day 2 will cover CIFAR10 image classification with Convolutional Neural Network and a simple example using Recurrent Neural Network.
* All coding will be done using Python 3 and PyTorch 1.8.
* Basic knowledge on Python and Object Oriented Programming is prerequisite for this course.
Contents
- Day 1 - AM : Linear model
- Day 1 - PM : Multi-Layer Perceptron
- Day 2 - AM : Convolutional Neural Network
- Day 2 - PM : Recurrent Neural Network
What we cover
- Training linear model for Single/Multi-variable regression
- Activation functions
- Loss functions
- Optimizer
What we cover
- Multi-Layer Perceptron for linear regression
- Overfitting
- Hyper-parameters
- Advanced techniques: Batch normalization, Xavier initialization, dropout
What we cover
- Image classification for MNIST
- Logistic model, cross entropy function
- Convolutional Neural Network
- Gradient Vanishing
What we cover
- Recurrent Neural Network
- Long Short Term Memory to predict a sine function
KAIST Idea Factory - [Deep learning alone]
Stanford [CS231n]
Pytorch document [1.5.0]