Deep Lab v3 +
Image Segmentation, Deep Lab v3
Deep Learning
Mask R-CNN
Image Segmentation, Mask R-CNN
U-net
Image Segmentation, U-net
ConDeconvolutional Network
Image Segmentation, Deconvolutional Network
FCN (Fully Convolution Network for Semantic Segmentation)
Image Segmentation, FCN
Image Segmentation이란
Image Segmentation
SSD (Single Shot MultiBox Detector)
Object Detection, YOLO v2 & YOLO 9000
YOLO v2 & YOLO 9000
Object Detection, YOLO v2 & YOLO 9000
YOLO v1
Object Detection, YOLO, You Only Look Once
Fast,Faster R-CNN
Object Detection, Faster R-CNN
R-CNN
Object Detection, R-CNN
Object Detection이란
Object Detection,1-stage Detector,2-stage Detector
MobileNet, SqueezeNet, DenseNet
MobileNet, SqueezeNet, DenseNet
Inception v1,v2,v3
Inception, 1x1 Conv, GoogleNet
ZFNet & Network in Network
LeNet, AlexNet
LeNet & AlexNet
LeNet, AlexNet
Restricted Boltzmann Machine 코드 (pytorch)
Restricted Boltzmann Machine 2, Movie Recommendation
Restricted Boltzmann Machine 이론
Restricted Boltzmann Machine
(paper) Weights Uncertainty in Neural Networks
Bayes by Backprop
52.(paper) 24.Personalizing Dialogue Agents ; I have a dog, do you have pets too
Paper Review by Seunghan Lee
51.(paper) 23.Dialogue Natural Language Inference
Paper Review by Seunghan Lee
50.(paper) 22.CoQA ; A Conversational Question Answering Challenge
Paper Review by Seunghan Lee
49.(paper) 21.Reading Wikipedia to Answer Open-Domain Questions
Paper Review by Seunghan Lee
48.(paper) 20.Poly-encoders; Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
Paper Review by Seunghan Lee
47.(paper) 19.What Does BERT Look At ; An Analysis of BERT’s Attention
Paper Review by Seunghan Lee
46.(paper) 18.BERT ; Pre-training of Deep Bidirectional Transformers for Language Understanding
Paper Review by Seunghan Lee
45.(paper) 17.Improving Language Understanding by Generative Pre-Training
Paper Review by Seunghan Lee
44.(paper) 16.Deep contextualized word representations
Paper Review by Seunghan Lee
43.(paper) 15.Attention Is All You Need
Paper Review by Seunghan Lee
42.(paper) 14.Simple and Effective Multi-Paragraph Reading Comprehension
Paper Review by Seunghan Lee
41.(paper) 13.Deriving Machine Attention from Human Rationales
Paper Review by Seunghan Lee
40.(paper) 12.Attention is not not Explanation
Paper Review by Seunghan Lee
39.(paper) 11.Attention is not Explanation
Paper Review by Seunghan Lee
38.(paper) 10.Bi-Directional Attention Flow for Machine Comprehension
Paper Review by Seunghan Lee
37.(paper) 9.Adversarial Multi-task Learning for Text Classification
Paper Review by Seunghan Lee
36.(paper) 8.Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Paper Review by Seunghan Lee
35.(paper) 7.GloVe, Global Vectors for Word Representation
Paper Review by Seunghan Lee
34.(paper) 6.Text Understanding with the Attention Sum Reader Network
Paper Review by Seunghan Lee
33.(paper) 5.Neural Machine Translation by Jointly Learning to Align and Translate
Paper Review by Seunghan Lee
InfoGAN (Interpretable Representation Learning by Information Maximizing GAN)
Interpretable Representation Learning by Information Maximizing GAN
32.(paper) 4.Sequence to Sequence Learning with Neural networks
Paper Review by Seunghan Lee
LSGAN (Least Squares GAN) & ACGAN (Auxiliary Class GAN)
LSGAN & ACGAN
32.(paper) 3.Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
Paper Review by Seunghan Lee
31.(paper) 2.Distributed Representations of Words and Phrases and their Compositionality
Paper Review by Seunghan Lee
WGAN (Wasserstein GAN)
Wasserstein GAN
[code review] CGAN with pytorch
Conditional GAN, Pytorch
30.(paper) 1.Efficient Estimation of Word Representations in Vector Space
Paper Review by Seunghan Lee
28.(nlp) BERT (Bidirectional Encoder Representations from Transformers)
Neural Machine Translation, BLEU
CGAN (Conditional GAN)
Conditional GAN
27.(nlp) BERT 이전의 모델들 review
Neural Machine Translation
26.(nlp) BLEU
Neural Machine Translation, BLEU
GAN (Generative Adversarial Network)
Generative Adversarial Network
25.(nlp) Transformer 실습 (미완성)
Neural Machine Translation, Transformer
Auto Encoder
Auto Encoder
24.(nlp) Transformer 구현
Neural Machine Translation, Transformer
23.(nlp) Transformer
Neural Machine Translation, Transformer
(발표 자료) CNN
Convolutional Neural Network, ResNet, DenseNet
22.(nlp) Attention 구현
Neural Machine Translation, Attention
DenseNet 구현
Dense Unit, Dense & Transition Layer, Dense Net
21.(nlp) Attention
Neural Machine Translation, Attention
ResNet 구현
Residual Unit, Residual Layer, Residual Net
20.(nlp) seq2seq 구현
Neural Machine Translation, seq2seq
Vanilla CNN 구현
Basic of Convolutional Neural Network
19.(nlp) seq2seq
Neural Machine Translation, seq2seq
18.(nlp) Tagging
Name Entity Recognition, POS Tagging
17.(nlp) Text Classification with RNN, LSTM, Naive Bayes
Text Classification using RNN, LSTM, Naive Bayes
16.(nlp) CNN for NLP 실습
CNN for NLP
15.(nlp) CNN for NLP
CNN for NLP
13.(nlp) Pre-Trained Word Embedding
Pre-Trained Word Embedding
12.(nlp) GloVe
GloVe
11.(nlp) word2vec 실습
word2vec
10.(nlp) word2vec
word2vec
9.(nlp) Cosine Similarity & Recommendation System
Cosine Similarity, Recommendation System
8.(nlp) CHAR RNN
Char RNN
7.(nlp) Text Generation using LSTM
Text Generation using LSTM
6.(nlp) Text Generation using RNN
Text Generation using RNN
5.(nlp) Topic Modeling-LDA
Latent Dirichlet Allocation
4.(nlp) Topic Modeling-LSA
Latent Semantic Analysis
3.(basic) RNN Implementation
Recurrent Neural Network
2.(basic) Neural Net & Back Propagation 구현(2)
Neural Net, Back Propagation, Tensorflow
1.(basic) Neural Net & Back Propagation 구현(1)
Neural Net, Back Propagation, numpy