深度學習

教材模組教學目標

讓學生熟悉深度學習技術與相關應用

子模組一: 卷積神經網路 (Convolutional Neural Networks)

教學目標

介紹卷積神經網路基本原理,培養學生觀念與實作能力

透過作業,讓同學實作並視覺化神經網路中間層所擷取到的特徵

透過作業,讓同學了解不同filter size、stride所造成的影響

 

課程大綱

Introduction

Convolution Operation

Pooling

Variants of Basic Convolution Function

Structured Output

Data Types

Efficient Convolution Algorithms

Random or Unsupervised Features

Neuroscientific Basis for Convolutional Networks

實驗一: Convolutional Neural Network

實驗內容說明:
Use CIFAR-10 Dataset and build a convolutional neural network to do multi-class classification

 

可分享教材模組內容說明

In this problem, you will construct a Convolutional Neural Network (CNN) for image recognition using CIFAR-10 dataset. The CIFAR-10 dataset consists of 60,000  color images in 10 classes, with 6,000 images per class. There are 50,000 training images and 10,000 test images

  • Implement a CNN for image recognition using CIFAR-10. Analyze the effect of different settings including stride size and filter size. You should show the learning curve of training set and the final test error rate.
  • Show some of feature maps in hidden layers

 

所需實作平台配備與經費需求預估(以模組教學實作所需基本軟、硬體平台估算)

使用桌上型電腦、筆記型電腦,或者如參考規格之server(供多人使用):
CPU: intel i9 7900

GPU: Nvidia GTX 1080Ti 11GB

MB: x299

RAM: DDR4 16GB

HDD: 2TB

Power: 1000W

 

伺服器價格: 100,000元

可參考配置如下表

 

 

子模組二: 自編碼器 (Autoencoders)

教學目標

介紹自編碼器基本原理,培養學生觀念與實作能力

透過作業,讓同學了解不同種類的自編碼器

透過作業,讓學生實作重構MNIST-M資料集的自編碼器並觀察結果

 

課程大綱

Introduction

Undercomplete Autoencoders

Representational Power, Layer Size and Depth

Stochastic Encoders and Decoders

Denosing Autoencoders

Learning Manifolds with Autoencoders

Predictive Sparse Decomposition

Applications of Autoencoders

實驗二: Autoencoder

實驗內容說明:
Use MNIST-M Dataset and build an autoencoder to observe the learning curve and the generated samples

 

可分享教材模組內容說明

  • Please build an autoencoder to reconstruct mnist-m dataset, and show the reconstruction loss during training stage
  • Please refer to the “adversarial autoencoder”(AAE), implement an AAE and use t-SNE dimension reduction method to plot the encoding of training data

 

所需實作平台配備與經費需求預估(以模組教學實作所需基本軟、硬體平台估算)

使用桌上型電腦、筆記型電腦,或者如參考規格之server(供多人使用):
CPU: intel i9 7900

GPU: Nvidia GTX 1080Ti 11GB

MB: x299

RAM: DDR4 16GB

HDD: 2TB

Power: 1000W

 

伺服器價格: 100,000元

可參考配置如下表

聯絡窗口

姓名 電話 信箱
郭哲宇 0915516763 a7807656@gmail.com
王俊煒 0975266311 ula1592001@gmail.com
呂昱穎 0928051960 kevinlumail@gmail.com

 

可提供課程教材講義共627頁