Machine Learning Paper Review

The summary of papers are recorded in Issues (Inspired by kweonwooj's Github 👍)
Presentation slides are made for ~~biweekly seminar in SClab & Data analysis club~~ & ~~AI paper reading club~~.
Aug. 19, 2020 ~ Present

👉 Table of Contents

AI Theory
Medical AI
Computer Vision
Natural Language Processing and Large Language Model
Time Series Forecasting
Audio (Speech)
Clustering
XAI
Optimization
Classic Papers (before 2012)

📔 AI Theory

🩺 Medical AI

📺 Computer Vision

🔠 Natural Language Processing and Large Language Model

⌚ Time Series Forecasting

📻 Audio

🛍️ Clustering

📉 Optimization

🔍 XAI

✔️ Classic papers

In addition, we conducted a simple study that applied dimensionality reduction using PCA, RBM to classification problems.
🠊 Dimensionality reduction methods and Deep learning approach

Files

README.md

Latest commit

History

README.md

File metadata and controls

Machine Learning Paper Review

👉 Table of Contents

📔 AI Theory

1. Why do tree-based models still outperform deep learning on typical tabular data? | [grinsztajn2022.pdf]

2. Understanding softmax confidence and uncertainty | [pearce2021understanding.pdf]

🩺 Medical AI

1. [Domain Adaptation] Advancing medical imaging informatics by deep learning-based domain adaptation | [choudhary2020.pdf]

2. Annotation-Free Deep Learning-Based Prediction of Thyroid Molecular Cancer Biomarker BRAF (V600E) from Cytological Slides | [wang2023annotation.pdf]

3. Deep Learning Based Screening and Ancillary Testing for Thyroid Cytopathology | [dov2023deep.pdf]

4. Pathologist-level interpretable whole-slide cancer diagnosis with deep learning | [zhang2019pathologist.pdf]

5. Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images | [dov2021weakly.pdf]

6. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images | [campanella2019clinical.pdf]

7. Support Vector Machine based diagnostic system for thyroid cancer using statistical texture features | [gopinath2013support.pdf]

8. Classifying and segmenting microscopy images with deep multiple instance learning | [kraus2016classifying.pdf]

9. Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification | [hou2016patch.pdf]

10. Deep learning for identifying metastatic breast cancer | [wang2016deep]

11. Interactive thyroid whole slide image diagnostic system using deep representation | [chen2020interactive.pdf]

12. Pyramid tokens-to-token vision transformer for thyroid pathology image classification | [yin2022pyramid.pdf]

13. Automatic whole slide pathology image diagnosis framework via unit stochastic selection and attention fusion | [chen2021automatic.pdf]

📺 Computer Vision

1. [LeNet] Gradient-based learning applied to document recognition. | [lecun1998.pdf]

2. [ViT] An image is worth 16x16 words: Transformers for image recognition at scale | [dosovitskiy2020.pdf]

3. [2020Survey] Self-supervised visual feature learning with deep neural networks: A survey | [jing2020self.pdf]

4. [ISP] Architectural analysis of a baseline isp pipeline | [park2016.pdf]

🔠 Natural Language Processing and Large Language Model

1. [AQM+] Large-scale answerer in questioner's mind for visual dialog question generation | [lee2019.pdf]

2. [VLM] An introduction to vision-language modeling [bordes2024introduction.pdf]

⌚ Time Series Forecasting

1. [2021Survey] Time-series forecasting with deep learning: a survey | [lim2021.pdf]

2. [WaveNet] WaveNet: A generative model for raw audio | [van2016.pdf]

3. [LightGBM] LightGBM: A Highly Efficient Gradient Boosting Decision Tree | [ke2017.pdf]

4. [RNNsearch] Neural machine translation by jointly learning to align and translate | [bahdanau2014.pdf]

5. [Transformer] Attention is all you need | [vaswani2017.pdf]

6. [Fbprophet] Forecasting at scale | [taylor2018.pdf]

📻 Audio

1. [2020Survey] Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers | [akccay2020speech.pdf]

🛍️ Clustering

1. Clustering with deep learning: Taxonomy and new methods | [aljalbout2018clustering.pdf]

📉 Optimization

1. [Momentum] On the importance of initialization and momentum in deep learning. | [sutskever2013.pdf]

2. [Adam] Adam: A method for stochastic optimization. | [kingma2014.pdf]

3. [Dropout] Dropout: a simple way to prevent neural networks from overfitting. | [srivastava2014.pdf]

4. [Batch normalization] Batch normalization: Accelerating deep network training by reducing internal covariate shift. | [ioffe2015.pdf]

5. [HighwayNet] Training very deep networks. | [srivastava2015.pdf]

6. [He initialization] Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. | [he2015.pdf]

🔍 XAI

1. [2020Survey] Opportunities and challenges in explainable artificial intelligence (XAI): A survey | [das2020.pdf]

2. [MST+SHAP] Explainable machine learning in credit risk management | [bussmann2021.pdf]

✔️ Classic papers

1. [Turing Machine] On computable numbers, with an application to the Entscheidungsproblem. | [turing1936.pdf]

2. [Imitation Game] Computing machinery and intelligence. | [turing2009.pdf]

3. [Back-propagation] Learning representations by back-propagating errors. | [hinton1986.pdf]

4. [Deep belief net] Reducing the dimensionality of data with neural networks. | [hinton2006.pdf]

5. [Unsupervised Pretraining] Why does unsupervised pre-training help deep learning? | [erhan2010.pdf]

1. Why do tree-based models still outperform deep learning on typical tabular data? | `[grinsztajn2022.pdf]`

2. Understanding softmax confidence and uncertainty | `[pearce2021understanding.pdf]`

1. [Domain Adaptation] Advancing medical imaging informatics by deep learning-based domain adaptation | `[choudhary2020.pdf]`

2. Annotation-Free Deep Learning-Based Prediction of Thyroid Molecular Cancer Biomarker BRAF (V600E) from Cytological Slides | `[wang2023annotation.pdf]`

3. Deep Learning Based Screening and Ancillary Testing for Thyroid Cytopathology | `[dov2023deep.pdf]`

4. Pathologist-level interpretable whole-slide cancer diagnosis with deep learning | `[zhang2019pathologist.pdf]`

5. Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images | `[dov2021weakly.pdf]`

6. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images | `[campanella2019clinical.pdf]`

7. Support Vector Machine based diagnostic system for thyroid cancer using statistical texture features | `[gopinath2013support.pdf]`

8. Classifying and segmenting microscopy images with deep multiple instance learning | `[kraus2016classifying.pdf]`

9. Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification | `[hou2016patch.pdf]`

10. Deep learning for identifying metastatic breast cancer | `[wang2016deep]`

11. Interactive thyroid whole slide image diagnostic system using deep representation | `[chen2020interactive.pdf]`

12. Pyramid tokens-to-token vision transformer for thyroid pathology image classification | `[yin2022pyramid.pdf]`

13. Automatic whole slide pathology image diagnosis framework via unit stochastic selection and attention fusion | `[chen2021automatic.pdf]`

1. [LeNet] Gradient-based learning applied to document recognition. | `[lecun1998.pdf]`

2. [ViT] An image is worth 16x16 words: Transformers for image recognition at scale | `[dosovitskiy2020.pdf]`

3. [2020Survey] Self-supervised visual feature learning with deep neural networks: A survey | `[jing2020self.pdf]`

4. [ISP] Architectural analysis of a baseline isp pipeline | `[park2016.pdf]`

1. [AQM+] Large-scale answerer in questioner's mind for visual dialog question generation | `[lee2019.pdf]`

2. [VLM] An introduction to vision-language modeling `[bordes2024introduction.pdf]`

1. [2021Survey] Time-series forecasting with deep learning: a survey | `[lim2021.pdf]`

2. [WaveNet] WaveNet: A generative model for raw audio | `[van2016.pdf]`

3. [LightGBM] LightGBM: A Highly Efficient Gradient Boosting Decision Tree | `[ke2017.pdf]`

4. [RNNsearch] Neural machine translation by jointly learning to align and translate | `[bahdanau2014.pdf]`

5. [Transformer] Attention is all you need | `[vaswani2017.pdf]`

6. [Fbprophet] Forecasting at scale | `[taylor2018.pdf]`

1. [2020Survey] Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers | `[akccay2020speech.pdf]`

1. Clustering with deep learning: Taxonomy and new methods | `[aljalbout2018clustering.pdf]`

1. [Momentum] On the importance of initialization and momentum in deep learning. | `[sutskever2013.pdf]`

2. [Adam] Adam: A method for stochastic optimization. | `[kingma2014.pdf]`

3. [Dropout] Dropout: a simple way to prevent neural networks from overfitting. | `[srivastava2014.pdf]`

4. [Batch normalization] Batch normalization: Accelerating deep network training by reducing internal covariate shift. | `[ioffe2015.pdf]`

5. [HighwayNet] Training very deep networks. | `[srivastava2015.pdf]`

6. [He initialization] Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. | `[he2015.pdf]`

1. [2020Survey] Opportunities and challenges in explainable artificial intelligence (XAI): A survey | `[das2020.pdf]`

2. [MST+SHAP] Explainable machine learning in credit risk management | `[bussmann2021.pdf]`

1. [Turing Machine] On computable numbers, with an application to the Entscheidungsproblem. | `[turing1936.pdf]`

2. [Imitation Game] Computing machinery and intelligence. | `[turing2009.pdf]`

3. [Back-propagation] Learning representations by back-propagating errors. | `[hinton1986.pdf]`

4. [Deep belief net] Reducing the dimensionality of data with neural networks. | `[hinton2006.pdf]`

5. [Unsupervised Pretraining] Why does unsupervised pre-training help deep learning? | `[erhan2010.pdf]`