TonTon Huang Ph.D. | 痛痛 - Deep Learning 101

https://interactionx.pse.is/DLBook101 | https://interactionx.pse.is/DLMeetup101
YouTube | 台灣人工智慧社團 FB | Odysee
Deep Learning 101 Meetup
Taiwan’s pioneering and highest deep learning meetup, launched on 2016/11/11 @ 83F, Taipei 101
Deep Learning 101 創立初衷，是為了普及與分享深度學習及AI領域的尖端知識，深信AI的價值在於解決真實世界的商業問題。
https://deep-learning-101.github.io
https://github.com/Deep-Learning-101 | https://huggingface.co/DeepLearning101

如果想分享研究心得或產業相關題目，歡迎報名。
本讀書會採實名分享制，主要參與者分別來自不同公司的人工智慧研發團隊。
AI是一條孤獨且充滿不確定的惶恐旅程，花俏絢麗的收費課程或活動絕非通往成功的捷徑。
衷心感謝當時來自不同單位的AI同好參與者實名分享的寶貴經驗；如欲移除資訊還請告知。
由 TonTon Huang Ph.D. 發起，及其當時任職公司(台灣雪豹科技)無償贊助場地及茶水點心。

Welcome to Taiwan ! Prof. Yann LeCun @ 2017/06/29

在快速變動的全球局勢與本地產業環境下，您的營運是否正遭遇瓶頸？這些不僅是挑戰，更是導入AI、實現轉型升級的最佳契機。AI導入並非單純的技術採購，而是一場由上而下的企業變革。

【第一步】企業現況與需求訪談：了解商業模式、營運痛點與期望目標，定義出最具商業價值的AI應用場景。
【第二步】AI導入策略與藍圖規劃：量身打造清晰、務實的AI導入路線圖，包含技術架構、數據策略、預算規劃與預期效益。
【第三步】概念驗證 (PoC) 與模型開發：以最小成本、快速度建立一個可行的AI模型來驗證構想，確保方向正確，並依據反饋快速迭代。
【第四步】系統整合與全面導入：將成熟的AI模型無縫對接到您現有的系統，實現真正的自動化與智慧化。
【第五步】團隊賦能與技術培訓：不只交付工具，更交付知識。提供教育訓練，確保AI能真正落地生根，成為企業文化的一部分。

Prof. Hung-Yi Lee

EE.NTU

Deep Learning 101 - 大神 Q&A I & II
No. 16 @ 2018/02/02
深度學習界的大神們來台北101給大家解惑
疑難雜症都不用擔心

Prof. Winston Hsu

CSIE.NTU

On the Relationship among Convolution Attention and GNN
No. 49 @ 2022/05/06 @ 杜岳華

深度學習也可以學傅立葉轉換
 No. 47 @ 2020/12/04 @ 杜岳華

Machine Teaching
No. 31 @ 2019/06/28 @ Mark Liou

Model-Based Reinforcement Learning
No. 48 @ 2021/07/16 @ 翁崇恒

神經網路的黑執事
 No. 44 @ 2020/08/21 @ Mark Liou

Introduction to geometric deep learning with implementation
No. 37 @ 2020/01/10 @ 杜岳華

幾何深度學習是在幾何什麼的？
No. 43 @ 2020/07/24 @ 杜岳華

高維資料的降維演算法及視覺化
No. 39 @ 2020/03/20 @ 杜岳華

Modeling the Dynamics of SGD by Stochastic Differential EquationNo. 45 @ 2020/09/11 @ Mark Chang

information in the weightsNo. 42 @ 2020/06/19 @ Mark Chang

PAC Bayesian for Deep LearningNo. 38 @ 2020/02/14 @ Mark Chang

Transfer Learnings & Multitask LearningNo. 32 @ 2019/07/19 @ Mark Chang

Towards Principled Methods for Training Generative Adversarial NetworksNo. 19 @ 2018/05/11 @ Mark Chang

Domain adaptationNo. 29 @ 2019/03/08 @ Mark Chang

NLP Landing & Marchine Reading Comprehension
No. 41 @ 2020/05/29 @ Ian & Hsiang

Instance Segmentation No. 40 @ 2020/05/01 @ 顏志翰 (Bean)

Explainable Artificial IntelligenceNo. 36 @ 2019/12/13 @ Jiero Ho

High-Dimensional Continuous Control Using Generalized Advantage Estimation No. 34 @ 2019/10/04 @ Cecile Liu

Hardware Accelerators for Machine Learning No. 33 @ 2019/08/23 @ 林家銘

The Hackathon/Formosa Grand Challenge Between UsNo. 30 @ 2019/05/17 @ Ryan Chao

Deep knowledge representation and reasoningNo. 28 @ 2019/02/15 @ Chin-Hui Chen

Semi-Supervised Classification with Graph Convolutional NetworksNo. 27 @ 2019/01/11 @ Bean Yen

Machine Reading Comprehension No. 26 @ 2018/12/07 @ Nat Lee, Alice Hong, Ian Wang

No. 25 @ 2018/11/09 @ Deep Learning 101 2週年

SOC: Social-network Opinion and CommentNo. 24 @ 2018/10/12 @ Nat Lee, TonTon

Recommender SystemNo. 23 @ 2018/09/14 @ SAS

Deep Bilateral Learning for Real-Time Image Enhancement No. 22 @ 2018/08/17 @ 黃俊仁 (Ken Huang)

Dynamic Routing Between CapsulesNo. 21 @ 2018/07/06 @ Jiero Ho

VAE: A generative model for 2D anime character facesNo. 20 @ 2018/06/08 @ Nat Lee, Boris Lo, Alice Hong, Ian Wang

Deep Generative Models @ Deep Learning BookChapter 20 @ No.18 @ 2018/04/13

Approximate Inference @ Deep Learning Book Chapter 19 @ No.17 @ 2018/03/16

Confronting the Partition Function @ Deep Learning BookChapter 18 @ No.15 @ 2018/01/12

Monte Carlo Methods @ Deep Learning Book
Chapter 17 @ No.14 @ 2017/12/15 @ Ian Wang

Structured Probabilistic Models @ Deep Learning BookChapter 16 @ No. 12 @ 2017/10/27

Autoencoders @ Deep Learning Book
Chapter 14 @ No. 11 @ 2017/09/08

Linear Factor Models @ Deep Learning BookChapter 13 @ No. 10 @ 2017/08/11

Representation Learning @ Deep Learning Book Chapter 15 @ No. 09 @ 2017/07/07

Recurrent and Recursive Nets @ Deep Learning Book
Chapter 10 @ No. 07 @ 2017/05/05

Convolutional Networks @ Deep Learning BookChapter 9 @ No. 06 @ 2017/04/14

Optimization for Training Deep Models @ Deep Learning Book Chapter 8 @ No. 05 @ 2017/03/10

Page updated

Report abuse