Vu Nguyen Minh Duc

A journey of a thousand miles begins with a single step

[Vaishnavi @_vmlops]

Most people learn ML.

Few learn how to run ML in production.

This GitHub repo is basically an MLOps treasure map 🗺️

→ MLOps fundamentals
→ Courses & books
→ DataOps
→ Model deployment
→ Testing & monitoring
→ Infrastructure
→ Real-world ML systems
→ Papers & communities

If you’re serious about MLOps, bookmark this

"Awesome MLOps"

https://t.co/tRr9WYXraD

[Kirk Borne @KirkDBorne]

Textbook: “Mathematics for Computer Science”

Free 920-page PDF download, from MIT:
https://t.co/QnexP4k4ET

[Dr. Ganapathi Pulipaka 🇺🇸 @gp_pulipaka]

Natural Language Processing and Large Language-Model - Free eBook!

A new 2026 Springer Open Access book bridging foundational NLP with modern LLMs through theory, executable code, and case studies to read.

Covers:

• Neural Networks + Distributed Representations
• Sequence Generation + Language Models
• Pre-trained Large Models
• Tokenization + Word Segmentation
• Transformer, BERT, GPT + ERNIE
• Sentiment Classification
• Information Extraction
• Semantic Text Matching
• PEGASUS Text Summarization
• Machine Reading Comprehension
• Machine Translation
• Question Answering with LLM
• RLHF
• Fine-tuning + Deployment

Includes executable Jupyter notebooks and datasets, with free cloud-based resources for running and modifying the models.

#BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #Books #100DaysofCode

Amazon:
https://t.co/zRjzBfTwd2

FREE Open Access eBook:
https://t.co/4rXSFGB9kp

[Dr. Ganapathi Pulipaka 🇺🇸 @gp_pulipaka]

Machine Learning Methods — Free 874-Page Open Access Textbook!

Hang Li’s Springer 2026 book, a follow up 2nd Edition is an enormous reference spanning the four core branches of Machine Learning:

• Supervised Learning
• Unsupervised Learning
• Deep Learning
• Reinforcement Learning
• 80+ essential algorithms
• GBDT + EM Algorithm
• Transformers
• Diffusion Models
• PPO
• Mathematical formulations + intuitive explanation
• Practical examples+ Machine Learning real-world relevance

At 874 pages with 260 illustrations, it is designed for advanced undergraduate/graduate students of ML, educators and AI professionals. Springer explicitly marks the textbook Open Access, free and unlimited access.

#BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Mathematics #Programming #Books #Coding #100DaysofCode

Free Open Access:
https://t.co/p6SUqS1C8K

Amazon:
https://t.co/6phu6OJOkh

[santi @santtiagom_]

todo lo que necesitas para aprender System Design desde 0:

[Mehmet Songur @mehmetsongur_]

Makine öğrenmesinden veri görselleştirmeye, zaman serisi verilerinden finansal verilere 34 farklı kategoride 920 açık kaynak Python projesine aşağıdaki linkten ulaşabilirsiniz…

🔗 https://t.co/LSTzxkPZnv

[lumxss @bkdgiffug]

剑桥这回直接扔王炸了！！

AI & ML经典教材全集直接免费开放，PDF随便下。

想学机器学习又不想被割韭菜买高价课的，这十本刷完，底子基本就硬了。

顺序从易到难排好了：

1️⃣ 《机器学习理解》——理论算法一把抓，零基础入门首选
🔗 https://t.co/fylTw37bOl
2️⃣ 《机器学习数学基础》——数学底子弱的先把这本补上
🔗 https://t.co/yykNLQmdfv

3️⃣ 《机器学习算法��数学分析》——深入数学原理
🔗 https://t.co/MEvgkXoHYy
4️⃣ 《深度学习理论原理》——搞懂DL���后的理论根基
🔗 https://t.co/ig93KOQRPn

5️⃣ 《神经网络与机器学习》——神经网络的系统讲解
🔗 https://t.co/cTMBvJz6Ny
6️⃣ 《图深度学习》——图神经网络入门必读
🔗 https://t.co/RJeCqCstml

7️⃣ 《机器学习的算法视角》——从算法角度重新理解ML
🔗 https://t.co/VT0YnKdUdO
8️⃣ 《概率论：理论与实例》——概率基础打牢
🔗 https://t.co/NqVoIZGGYg

9️⃣ 《应用概率基础》——概率论实战应用
🔗 https://t.co/FrxqQER3mQ
🔟 《高级数据分析》——数据科学进阶必备
🔗 https://t.co/Zt74B21nrf

说句实话，这些书没一本是轻松的，别指望躺着翻完。
但只要你能硬啃下来两三本，比听群里吹一年AI牛逼都管用。

[Tom Dörr @tom_doerr]

Implements 35 production-grade agentic AI architectures as runnable classes with comparative benchmarks.

https://t.co/jLl89WZ80p

[Kirk Borne @KirkDBorne]

"Domain-Specific Small Language Models: Efficient AI for local deployment" available at https://t.co/K10yQCh9cU via @ManningBooks

[Kirk Borne @KirkDBorne]

Deep Learning with C++ — Design and deploy neural networks using CUDA for high-performance AI in C++

Get the book at https://t.co/RzMRhYihTE from @PacktPublishing @PacktDataML

[Kirk Borne @KirkDBorne]

System Design for the LLM Era — Patterns and Principles for Production-grade AI Architecture: https://t.co/fC3z5rCAc3
+
Find more best-selling AI/ML books by @PacktPublishing @PacktDataML here: https://t.co/n3NqGKpTw2

[lumxss @bkdgiffug]

想深入搞LLM推理的同学，这套东西值得关注。

有人整理了一份LLM工程师训练手册，每天30分钟，练10周，一共50课。不是那种拼凑的Demo，是真带你从头搭生产级技术栈：

1️⃣ 建思维模型，搞懂Decode为什么卡显存、Prefill为什么卡算力
2️⃣ 啃vLLM源码，PagedAttention和调度器逻辑一个不落
3️⃣ 上Prometheus、Grafana盯着TTFT和队列
4️⃣ 直接干1000+并发压测，FP8、INT4量化取舍讲透
学完手里有一套能跑的生产级技术栈，外加一份能拿出手的跑分报告。
🔗 https://t.co/uOXmUkEBOY
顺手点个star。作者还在给每个主题写长文，第一篇讲GPU到底怎么干活的，已经发了。

[Kirk Borne @KirkDBorne]

Machine Learning System Design Interview: https://t.co/bC5LsGO03N v/ @bytebytego

🔵 10 real questions & detailed solutions
🔵 211 diagrams to visually explain how various systems work
🔵 7-step framework to solve any #ML system design question

#DataScience #DataScientist

[Kirk Borne @KirkDBorne]

Hands-On Mathematical Optimization with Python: https://t.co/PRusR4dKpe

“…presents the key ingredients of an optimization problem and the choices one needs to make when modeling a real-life problem mathematically. Topics covered range from linear and network optimization to convex optimization and optimizations under uncertainty. The book's Python code snippets, alongside more than 50 Jupyter notebooks on the author's GitHub, allow students to put the theory into practice and solve problems inspired by real-life challenges.”

[Kirk Borne @KirkDBorne]

"MCMC from Scratch — Practical Introduction to Markov Chain Monte Carlo" — available at https://t.co/AqwfKhbKIX

From the Back Cover:

"This textbook explains the fundamentals of Markov Chain Monte Carlo (MCMC) without assuming advanced knowledge of mathematics and programming. MCMC is a powerful technique that can be used to integrate complicated functions or to handle complicated probability distributions. MCMC is frequently used in diverse fields where statistical methods are important – e.g. Bayesian statistics, quantum physics, machine learning, computer science, computational biology, and mathematical economics. This book aims to equip readers with a sound understanding of MCMC and enable them to write simulation codes by themselves."

"The content consists of six chapters. Following Chapter 2, which introduces readers to the Monte Carlo algorithm and highlights the advantages of MCMC, Chapter 3 presents the general aspects of MCMC. Chapter 4 illustrates the essence of MCMC through the simple example of the Metropolis algorithm. In turn, Chapter 5 explains the HMC algorithm, Gibbs sampling algorithm and Metropolis-Hastings algorithm, discussing their pros, cons and pitfalls. Lastly, Chapter 6 presents several applications of MCMC. Including a wealth of examples and exercises with solutions, as well as sample codes and further math topics in the Appendix, this book offers a valuable asset for students and beginners in various fields."

[Kirk Borne @KirkDBorne]

Explorations in Monte Carlo Methods (Undergraduate Texts in Mathematics): https://t.co/QNOJH53tyA

From the Back Cover:

"Monte Carlo methods are among the most used and useful computational tools available today, providing efficient and practical algorithims to solve a wide range of scientific and engineering problems. Applications covered in this book include optimization, finance, statistical mechanics, birth and death processes, and gambling systems."

"Explorations in Monte Carlo Methods provides a hands-on approach to learning this subject. Each new idea is carefully motivated by a realistic problem, thus leading from questions to theory via examples and numerical simulations. Programming exercises are integrated throughout the text as the primary vehicle for learning the material. Each chapter ends with a large collection of problems illustrating and directing the material."

"This book is suitable as a textbook for students of engineering and the sciences, as well as mathematics. The problem-oriented approach makes it ideal for an applied course in basic probability and for a more specialized course in Monte Carlo methods. Topics include probability distributions, counting combinatorial objects, simulated annealing, genetic algorithms, option pricing, gamblers ruin, statistical mechanics, sampling, and random number generation."

[Probability and Statistics @probnstat]

Online Bayesian Learning

Online Bayesian learning is the process of updating our beliefs about an unknown parameter or model as new data arrive sequentially.

Instead of retraining from scratch, we maintain a posterior distribution and update it with each observation:

Prior → New data → Posterior → Next prediction

Why is it useful?

• Statistics: sequential inference, Bayesian filtering, adaptive experiments & uncertainty quantification.
• Machine Learning: online prediction, concept drift, Bayesian neural networks & personalized models.
• Reinforcement Learning: uncertainty-aware exploration, Bayesian bandits, model-based RL & learning under partial information.

The key advantage: you don't just learn a point estimate—you continuously learn a distribution over what you believe.

That makes online Bayesian learning especially powerful when data arrive continuously and decisions must be made under uncertainty.

[Chieh-Hsin (Jesse) Lai @JCJesseLai]

🚀 v3 is out!

We’ve just updated 《The Principles of Diffusion Models》 on arXiv, ahead of its @mitpress MIT Press publication in 2027.

What’s new:
✨ A new “Road Ahead” chapter on discrete diffusion
🛠️ Major restructuring, including diffusion solvers chapter
🧭 Reader guides for each chapter

With continuous diffusion for language making a comeback, many of the same principles in the book can carry over.

Check out the new version (link in thread)!

w/ @DrYangSong, @gimdong58085414, @mittu1204, @StefanoErmon

[灰狐 @huihoo]

Free book, 640 Pages
The Scientist and Engineer's Guide to Digital Signal Processing
https://t.co/7q1mXAlrXP

史密斯 (Steven W. Smith) 博士是
《科学家和工程师数字信号处理指南》的作者
该书是Amazon网站上数字信号处理（DSP）类书籍销量第一的著作（在700多种同类书籍中名列前茅）

史密斯专注开发用于医疗、安防和工业领域的新型成像系统
史密斯也是 Tek84 公司创始人和总裁
该公司是一家专注于成像和仪器系统的研发机构
https://t.co/vz1kxtcfde

[孤桜ETH @GYLQ520]

去年想搞清楚LLM到底怎么工作的，翻了不少教程，要么只讲概念不写代码，要么直接上transformers库把底层全封装了，看完还是懵。

这个项目（Train LLM From Scratch）用纯PyTorch从零实现Transformer，没有trl、peft、transformers这些依赖，
每一步都拆开给你看：数据怎么变成token、模型怎么搭（MLP→注意力→多头→Transformer块→完整模型）、预训练怎么跑、SFT怎么教模型回答问题、Reward Model怎么打分、DPO/PPO/GRPO怎么对齐，整个链路清清楚楚。

代码里每个模块都有解释和预期输出，单GPU就能跑百万到十亿参数的模型，硬件参考也标得挺细。

🔗 地址：https://t.co/cnP1bFj6gu