Deep Learning

[DL-1] 學習建議：建議先優先完成 [DL-1A] 與 [DL-1B] 兩個課程模組，以快速建立對深度學習整體流程的基本認識與概念架構。接著閱讀 [DL-1C] 中的論文，以掌握醫學影像領域深度學習的概念與應用概覽。如有興趣，則可進一步研讀 [DL-1D]，加強 PyTorch 在一般影像上的實作與練習。

[DL-1A]

Introduction to Deep Learning with PyTorch・DataCamp・4 Hours Course

Learn the power of deep learning in PyTorch. Build your first neural network, adjust hyperparameters, and tackle classification and regression problems.

[DL-1B]

Intermediate Deep Learning with PyTorch・DataCamp・4 Hours Course

Learn about fundamental deep learning architectures such as CNNs, RNNs, LSTMs, and GRUs for modeling image and sequential data.

[DL-1C]

Paper Reading

• Deep Learning: A Primer for Radiologists・Gabriel Chartrand, Phillip M. Cheng, Eugene Vorontsov, Michal Drozdzal, Simon Turcotte, Christopher J. Pal, Samuel Kadoury, An Tang・Radio Graphics (2017)

• Deep Learning: An Update for Radiologists・Phillip M. Cheng, Emmanuel Montagnon, Rikiya Yamashita, Ian Pan, Alexandre Cadrin-Chênevert, Francisco Perdigón Romero, Gabriel Chartrand, Samuel Kadoury, An Tang・Radio Graphics (2021)

[DL-1D]

Deep Learning for Images with PyTorch・DataCamp・4 Hours Course

Apply PyTorch to images and use deep learning models for object detection with bounding boxes and image segmentation generation.

[DL-2] 學習建議：在 [DL-2A] 與 [DL-2B] 課程模組中，採用「閱讀 → 實作 → 閱讀 → 實作」的迭代方式進行學習，逐步掌握深度學習開發流程中的各個環節細節，並理解演算法的原理與應用實例。搭配 [DL-2-ShortVideos-1]、[DL-2-ShortVideos-2]、[DL-2-Visual-1] 提供圖像化的簡明說明，有助於快速建立關於深度學習的初步架構。 

[DL-2A]
Biomedical Image Analysis in Python・DataCamp・4 Hours Course (Intermediate)

In this introductory course, you'll learn the fundamentals of image analysis using NumPy, SciPy, and Matplotlib. You'll navigate through a whole-body CT scan, segment a cardiac MRI time series, and determine whether Alzheimer’s disease changes brain structure. Even if you have never worked with images before, you will finish the course with a solid toolkit for entering this dynamic field.

[DL-2B]
Detecting COVID-19 with Chest X-Ray using PyTorch・Guided Project・2 Hours Course (Intermediate)

Create custom Dataset and DataLoader in PyTorch and Train a ResNet-18 model in PyTorch to perform Image Classification.

[DL-2-Visual-1]

Brief Visual Introduction to Deep Learning

• Neural Networks from Scratch・Allison George・2021
  
  

• CNN Explainer・Jay Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, and Polo Chau
  
  

• playground.tensorflow.org・Daniel Smilkov and Shan Carter

[DL-3] 學習建議：建議先完成 [DL-3A]，以建立大型語言模型（Large Language Models, LLM）的應用與原理概念。接著透過 [DL-3B] 學習 Transformer 架構及其 Python 實作。最後於 [DL-3C] 中，運用 PyTorch 進行 Transformer 模型訓練，系統性掌握 LLM 核心技術。

[DL-3A]

Large Language Models (LLMs) Concepts・DataCamp・2 Hours Course (Beginner)

Discover the full potential of LLMs with our conceptual course covering LLM applications, training methodologies, ethical considerations, and latest research.

[DL-3B]

Introduction to LLMs in Python・DataCamp・ 4 Hours Course (Intermediate)

Learn the nuts and bolts of LLMs and the revolutionary transformer architecture they are based on!

[DL-3C]

Transformer Models with PyTorch・DataCamp・2 Hours Course (Advanced)

What makes LLMs tick? Discover how transformers revolutionized text modeling and kickstarted the generative AI boom.

[DL-4] 學習建議：建議以 [DL-4A] 作為核心教材，系統性涵蓋深度學習理論與實作，讀者應盡可能完整閱讀並搭配程式實作，以建立紮實的理解與應用能力。若希望進一步強化理論基礎，建議閱讀 [DL-4B]，以深入掌握深度學習背後的數學與統計原理。對數學理論研究發展有興趣者，可進一步研讀 [DL-4C]。若希望輕鬆認識深度學習的發展歷程，[DL-4D] 提供易讀的敘事性介紹，可作為延伸閱讀。

TBD