CS3048701: Deep Learning for Natural Language Processing

Lecture: Thursday, 8:10~10:00

Discussion: Wednesday, 16:30~17:20


Instructor: at

Teaching Assistants: ùW, Ckp, [a, dA, dF|


Date Syllabus Homework
3/1 Course Overview
3/7 HW1-1: Introduction to Python & Data
3/8 Introduction to NLP & Deep Learning
3/14 HW1-2: Introduction to TensorFlow & Data
3/15 Backpropagation
3/21 HW1-3: Backpropagation
3/22 Classic Representations & Language Modeling
3/28 HW2: Introduction to Keras & Data
3/29 Neural Language Modeling & Word Embeddings
4/4 Break
4/5 Break
4/11 HW3: Word Embeddings & Recurrent Neural Networks & Data
4/12 Topic Models & Recurrent Neural Networks
4/18 Break
4/19 Break
4/25 HW4: Convolutional Neural Networks & Data
4/26 Convolutional Neural Networks
5/2 Discussion on Homework 4 & HW5 Preparation
5/3 Paragraph Embeddings & Attention
5/9 Break & Submit Your Member List!
5/10 Advanced Structures
5/16 HW5: Generative Adversarial Network & Data
5/17 Cycle GAN & Conditional GAN Submit Your Research Topic
5/23 IRGAN
5/24 Speech Recognition with Deep Learning Methods (Mr. Ming-Han Yang, Delta Electronics, Inc.)
5/30 Discussion on Homework 5
5/31 Machine Comprehension with Deep Learning (Mr. Wen-Chin Huang, NTU & Academia Sinica)
6/6 Break for Your Final Project
6/7 Break for Your Final Project
6/13 Break for Your Final Project
6/14 7. o LoD oG Dank Learning: Generating Memes Using Deep Neural Networks
29. o oG An Extended Sentiment Dictionary Approach with TF-IDF to Enhance Sentiment Analysis Taking the Dcard Job forum as an example
25. ]ot oG Very Deep Convolution Networks for Large-Scale Image Recognition
30. oӡG Deep Music Genre
10. Bow doa o@
17. io oW LoG Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model
11. o oG Explaining and Harnessing Adversarial Examples@
5. o io HotG Deep Learning for Event-Driven Stock Prediction
6/20 1. fo Po }oG Recognition of Pornographic Web Pages by Classifying Texts and Images
3. o oM oۡG Visual Attribute Transfer through Deep Image Analogy
2. o do otG SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
8. Go \o oġG LSTM-based deep learning models for non-factoid answer selection
6/21 20. o oG MobileNetV2: Inverted Residuals and Linear Bottlenecks
27. o oM oۡG Visual Attribute Transfer Through Deep Image Analogy
9. ioE oo IoG Using Neural Networks to Predict Emoji Usage from Twitter Data
19. o doߡG Poker-CNN a pattern learning strategy for making draws and bets in poker games using convolutional networks
13. o o͡G Playing Atari with Deep Reinforcement Learning
4. Lo@ io foӡG Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks
23. Ho@ owG Car Plate Recognition Based on CNN Using Embedded System with GPU
28. }ovG Stacked Hourglass Networks for Human Pose Estimation
6/27 18. ioF oʡG Building Energy Consumption Prediction: An Extreme Deep Learning Approach
6. o o@ oRG A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks
22. o co doG Generating Chinese Classical Poems with RNN Encoder-Decoder
12. o BojG Comment Abuse Classification with Deep Learning@
6/28 15. EoE fo do¡G Sentiment Analysis on Movie Reviews using Recursive and Recurrent Neural Network Architectures
24. LoA ox oaG Extractive Summarization using Deep Learning
21. oo ioǡG Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
14. oR oG Very Deep Convolutional Networks for Text Classification
16. o oPG Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
26. o doM o{G Mask R-CNN for Object Detection and Segmentation