lvtaoo (@lvtaoo) 's Twitter Profile
lvtaoo

@lvtaoo

ID: 48950710

calendar_today20-06-2009 07:10:03

828 Tweet

17 Takipçi

590 Takip Edilen

Harsh (@theglobalminima) 's Twitter Profile Photo

Most classical ML books only talk about learning parameters. They lack > inference algorithms (MC-MC, EM) > Neural Networks as probabilistic function approximations > Bayesian DL, VAEs > ML models in PGM terms Kevin Murphy’s Probabilistic ML bridges these gaps. It talks about

Most classical ML books only talk about learning parameters. They lack

> inference algorithms (MC-MC, EM)
> Neural Networks as probabilistic function approximations 
> Bayesian DL, VAEs
> ML models in PGM terms

Kevin Murphy’s Probabilistic ML bridges these gaps. It talks about
Carlos E. Perez (@intuitmachine) 's Twitter Profile Photo

1/11 Everyone thinks you need to spend millions on retraining to make AI smarter. What if the genius-level reasoning was already there, just hidden? A new paper (from Harvard) I just read suggests we've been looking in the wrong place. And the solution is wild. 🤯 🧵👇 2/11

1/11 

Everyone thinks you need to spend millions on retraining to make AI smarter.

What if the genius-level reasoning was already there, just hidden?

A new paper (from Harvard) I just read suggests we've been looking in the wrong place. And the solution is wild. 🤯

🧵👇

2/11
Victor (@victor_explore) 's Twitter Profile Photo

The University of Michigan dropped a full Deep Learning for Computer Vision lecture series—22 videos, no paywall. > neural nets & backprop explained from scratch > CNNs, RNNs, attention, and generative models > even detection, segmentation, and reinforcement learning

The University of Michigan dropped a full Deep Learning for Computer Vision lecture series—22 videos, no paywall.  

> neural nets & backprop explained from scratch  
> CNNs, RNNs, attention, and generative models  
> even detection, segmentation, and reinforcement learning
Piotr Pomorski (@ptrpomorski) 's Twitter Profile Photo

- LR is mostly about L1 (lasso) or L2 (ridge) penalty - Naive Bayes is alpha - Decision tree nobody uses as a standalone algorithm but needs to be learnt how it works - Random forest is all about max depth, no. of estimators, max features (cannot be all of them), min. samples

Probability and Statistics (@probnstat) 's Twitter Profile Photo

Kernel PCA (kPCA) is an advanced machine learning technique for non-linear dimensionality reduction. It uses the "kernel trick" to map data into a high-dimensional feature space where complex, non-linear patterns become linear. Standard PCA is then applied in this new space. This

Kernel PCA (kPCA) is an advanced machine learning technique for non-linear dimensionality reduction. It uses the "kernel trick" to map data into a high-dimensional feature space where complex, non-linear patterns become linear. Standard PCA is then applied in this new space. This
LangChain (@langchainai) 's Twitter Profile Photo

🔒 Custom LLM Integration A production-ready solution that seamlessly integrates private LLM APIs into LangChain and LangGraph 1.0.0+ applications. Features authentication flows, logging, tool integration, and state management. 👉 Explore the full implementation:

🔒 Custom LLM Integration

A production-ready solution that seamlessly integrates private LLM APIs into LangChain and LangGraph 1.0.0+ applications. Features authentication flows, logging, tool integration, and state management.

👉 Explore the full implementation:
Kirk Borne (@kirkdborne) 's Twitter Profile Photo

Tutorials on Statistical Tests of Hypothesis: ANOVA; Chi Square; F-Test; Granger Causality; Likelihood-Ratio; Log Rank; Welch; Z-Test; +more... bit.ly/2EoA9NJ ———— #DataScience #Statistics #DataLiteracy #StatisticalLiteracy ——— ➕See this book: amzn.to/2W2EcpD

Tutorials on Statistical Tests of Hypothesis: ANOVA; Chi Square; F-Test; Granger Causality; Likelihood-Ratio; Log Rank; Welch; Z-Test; +more...
bit.ly/2EoA9NJ
————
#DataScience #Statistics #DataLiteracy #StatisticalLiteracy 
———
➕See this book: amzn.to/2W2EcpD
Mustafa (@mustafa_kh4n) 's Twitter Profile Photo

most books teach algorithms. this one teaches how to think about them. > this book sharpens your reasoning, not just your syntax; > perfect for students, interview preppers, and anyone who wants to solve problems like a computer scientist

most books teach algorithms. this one teaches how to think about them.

> this book sharpens your reasoning, not just your syntax; 
> perfect for students, interview preppers, and anyone who wants to solve problems like a computer scientist
karminski-牙医 (@karminski3) 's Twitter Profile Photo

又一个 DeepSeek-OCR 客户端!全 Rust 实现! 这个兼容性写得非常好,windows/linux/mac 下都能运行,而且还支持CPU或者GPU推理。并且,推理引擎也是用 Rust 写的! 程序会自动下载模型,内置双源(Hugging Face + ModelScope)模型下载,所以不出境游也能用。 地址:github.com/TimmyOVO/deeps…

又一个 DeepSeek-OCR 客户端!全 Rust 实现!

这个兼容性写得非常好,windows/linux/mac 下都能运行,而且还支持CPU或者GPU推理。并且,推理引擎也是用 Rust 写的!

程序会自动下载模型,内置双源(Hugging Face + ModelScope)模型下载,所以不出境游也能用。

地址:github.com/TimmyOVO/deeps…
白骏知识分享 (@cj3214567667) 's Twitter Profile Photo

史上最全搞钱书籍,看完一半,年入百万。 【史上最全搞钱书籍】 立即保存:pan.quark.cn/s/58be1d4003b8

史上最全搞钱书籍,看完一半,年入百万。

【史上最全搞钱书籍】
立即保存:pan.quark.cn/s/58be1d4003b8
Math Cafe (@riazi_cafe_en) 's Twitter Profile Photo

Stanford's "Convex Optimization" Videos & Lecture Notes & more Course 1: see.stanford.edu/Course/EE364A Course 2: see.stanford.edu/Course/EE364B

Stanford's "Convex Optimization"  Videos & Lecture Notes & more  

Course 1: see.stanford.edu/Course/EE364A
Course 2: see.stanford.edu/Course/EE364B
Valeriy M., PhD, MBA, CQF (@predict_addict) 's Twitter Profile Photo

Kolmogorov Arnold Attention is all one needs 🧠🔍 KArAt: Learnable (and more explainable) Attention This paper swaps the fixed softmax for Kolmogorov-Arnold Attention (KArAt)—a learnable operator. Why care: • Clearer attention maps: heads often lock onto whole objects, aiding

Kolmogorov Arnold Attention is all one needs 

🧠🔍 KArAt: Learnable (and more explainable) Attention
This paper swaps the fixed softmax for Kolmogorov-Arnold Attention (KArAt)—a learnable operator.

Why care:
• Clearer attention maps: heads often lock onto whole objects, aiding