الگوریتمها چطور کار میکنن؟

Basic
I. II. III. One Node Four Nodes One Hidden Layer
IV. Three Inputs
V. Seven Layers

Advanced:
1. Mixture of Experts (MOEs)
2. Recurrent Neural Network (RNN)
3. Mamba
4. Matrix Multiplication
5. LLM Sampling
6. MLP in PyTorch
7. Backpropagation
8. Transformer
9. Batch Normalization
10. Generative Adversarial Network (GAN)
11. Self Attention
12. Dropout
13. Autoencoder
14. Vector Database
15. CLIP
16. Residual Network (ResNet)
17. Graph Convolution Network (GCN)
18. SORA’s Diffusion Transformer (DiT)
19. Gemini 1.5's Switch Transformer
20. Reinforcement Learning with Human Feedback (RLHF)

#منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

صحبتهای دکتر میثم عسگری در مورد
Prompt Engineering
چگونه با #هوش_مصنوعی صحبت کنیم؟!

#منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

یک لیست گلچین شده از پرامپت های GPT هایی که بالاترین امتیاز را گرفتن به همراه کلی منبع و مقاله های مرتبط برای یادگیری prompt engineering توی این ریپو است.

https://github.com/ai-boost/awesome-prompts

#منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

چت بات Grok توئیتر سابق اوپن سورس شد
https://github.com/xai-org/grok-1

📣 مقاله:
▪️ OLMo: Accelerating the Science of Language Models

#هوش_مصنوعی #الگوریتمها #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

خلاصه ای مفید و جامع از مدلهای دیفیوژن

▪️ Tutorial on Diffusion Models for Imaging and Vision

#هوش_مصنوعی #منابع #کتاب #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

اگه درگیر تقویت (یا یادگیری) SQL هستین یا میخواین برای پوزیشن های Data Engineer یا Data Analyst اقدام کنید👇

https://dataexpert.io/questions

یه سری سوال با لول های سختی متفاوت گذاشته که میتونید توی همون وبسایتشون هم کد بزنید و هم خروجی بگیرید!

#پایگاه_داده #کتاب #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

This is a set of scripts that may be helpful to people looking for a career in research.

▪️Research Career Tools

Find My Citers: This script helps find people who have cited your papers, which can be useful to find recommendation letter writers for job or visa applications.

#هوش_مصنوعی #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

استاد Andrew Ng فرمودند:

Last week, I described four design patterns for AI agentic workflows that I believe will drive significant progress this year: Reflection, Tool use, Planning and Multi-agent collaboration. Instead of having an LLM generate its final output directly, an agentic workflow prompts the LLM multiple times, giving it opportunities to build step by step to higher-quality output. Here, I'd like to discuss Reflection. For a design pattern that’s relatively quick to implement, I've seen it lead to surprising performance gains.

You may have had the experience of prompting ChatGPT/Claude/Gemini, receiving unsatisfactory output, delivering critical feedback to help the LLM improve its response, and then getting a better response. What if you automate the step of delivering critical feedback, so the model automatically criticizes its own output and improves its response? This is the crux of Reflection.

Take the task of asking an LLM to write code. We can prompt it to generate the desired code directly to carry out some task X. After that, we can prompt it to reflect on its own output, perhaps as follows:

Here’s code intended for task X:
[previously generated code]
Check the code carefully for correctness, style, and efficiency, and give constructive criticism for how to improve it.

Sometimes this causes the LLM to spot problems and come up with constructive suggestions. Next, we can prompt the LLM with context including (i) the previously generated code and (ii) the constructive feedback, and ask it to use the feedback to rewrite the code. This can lead to a better response. Repeating the criticism/rewrite process might yield further improvements. This self-reflection process allows the LLM to spot gaps and improve its output on a variety of tasks including producing code, writing text, and answering questions.

And we can go beyond self-reflection by giving the LLM tools that help evaluate its output; for example, running its code through a few unit tests to check whether it generates correct results on test cases or searching the web to double-check text output. Then it can reflect on any errors it found and come up with ideas for improvement.

Further, we can implement Reflection using a multi-agent framework. I've found it convenient to create two different agents, one prompted to generate good outputs and the other prompted to give constructive criticism of the first agent's output. The resulting discussion between the two agents leads to improved responses.

Reflection is a relatively basic type of agentic workflow, but I've been delighted by how much it improved my applications’ results in a few cases. I hope you will try it in your own work. If you’re interested in learning more about reflection, I recommend these papers:
- Self-Refine: Iterative Refinement with Self-Feedback, by Madaan et al. (2023)
- Reflexion: Language Agents with Verbal Reinforcement Learning, by Shinn et al. (2023)
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing, by Gou et al. (2024)

I’ll discuss the other agentic design patterns as well in the future.
https://www.deeplearning.ai/the-batch/issue-242/

#هوش_مصنوعی #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

با یک پرامپت کتاب کامل می‌نویسه و با فرمت EPUB خروجی میده
https://github.com/mshumer/gpt-author

#آموزش #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

Andrej Karpathy:
I added a quick crappy tutorial on how PyTorch layers are moved to C, with a few possibly helpful pointers:
https://github.com/karpathy/llm.c/blob/master/doc/layernorm/layernorm.md

#منابع #الگوریتمها #پایتون

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

صحبتهای دکتر میثم عسگری در مورد
Prompt Engineering
چگونه با #هوش_مصنوعی صحبت کنیم؟!

#منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

نظر شما راجب این توئیت استاد چیه ؟ آینده کجاست تحقیقات به سمت چه الگوریتمهایی هست؟
The Godfather of AI is at VivaTech!
Yann LeCun advises students coming into the industry:
"Don't work on LLM. This is in the hands of large companies, there's nothing you can bring to the table. You should work on next-gen AI systems that lift the limitations of LLMs.

پ.ن: علاقمند به خوندن کامنت‌های شما هستم.

#منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

مدلهایی که در هفته گذشته به صورت متن باز منتشر شدند.

- CogVLM2: multimodal conversational
- Yi 1.5 long context
- M2-BERT-V2, long-context encoder models
- Phi 3 small and medium + vision
- Falcon VLM
- Mistral 7B 0.3
- Aya 23: multilingual

#الگوریتمها #هوش_مصنوعی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

لیست جامع از cloud coding های انلاین

🔔 https://lambdalabs.com/service/gpu-cloud

🔔 https://colab.research.google.com/

🔔 Lightning.ai

🔔 https://modal.com/pricing

🔔 https://replicate.com/

🔔 https://huggingface.co/pricing

🔔 https://www.lepton.ai/

🔔 https://aws.amazon.com/sagemaker/train/ 📣
مهم هستش و خیلی بهتر از بقیه موارد گفته شده در بالا هستش.

پ.ن : اگه چیزی دیگه وجود داره کامنت کنید تا اضافه کنم

#الگوریتمها #منابع #پردازش_آنلاین

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

نظر شما راجب این توئیت استاد چیه ؟ آینده کجاست تحقیقات به سمت چه الگوریتمهایی هست؟
The Godfather of AI is at VivaTech!
Yann LeCun advises students coming into the industry:
"Don't work on LLM. This is in the hands of large companies, there's nothing you can bring to the table. You should work on next-gen AI systems that lift the limitations of LLMs.

پ.ن: علاقمند به خوندن کامنت‌های شما هستم.

#منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

لیست جامع از cloud coding های انلاین

🔔 https://lambdalabs.com/service/gpu-cloud

🔔 https://colab.research.google.com/

🔔 Lightning.ai

🔔 https://modal.com/pricing

🔔 https://replicate.com/

🔔 https://huggingface.co/pricing

🔔 https://www.lepton.ai/

🔔 https://aws.amazon.com/sagemaker/train/ 📣
مهم هستش و خیلی بهتر از بقیه موارد گفته شده در بالا هستش.

پ.ن : اگه چیزی دیگه وجود داره کامنت کنید تا اضافه کنم

#الگوریتمها #منابع #پردازش_آنلاین

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

چنلهای یوتیوب خوب و کاربردی الگوریتمهای هوش مصنوعی (قسمت اول)

1- Abhishek Thakur (Practical videos)
ویژگی پلی لیست :
Applied Machine Learning Framework, Tips & Tricks of machine learning

2- Ahlad Kumar (Deep learning, Theoretical )
ویژگی پلی لیست:
Deep Learning, Convolutional Neural Network, Neural Networks

3- Aladdin Persson (Content about: PyTorch, TensorFlow )
ویژگی پلی لیست:
PyTorch Tutorials, TensorFlow 2.0 Beginner Tutorials, Machine Learning Algorithms.

4- Andreas Mueller ( Content about: Machine learning )
ویژگی پلی لیست:
Applied Machine Learning

5- Data School ( Content about: Python, Machine learning, Theoretical )
ویژگی پلی لیست:
Introduction to Machine Learning , Data analysis in Python with Pandas, other talks videos and Python videos.

6-Henry AI Labs (Theoretical )
ویژگی پلی لیست:
Deep Learning Paper Summaries, Reinforcement Learning, Generative Adversarial Networks, Neural Network Design

7- Jeremy Howard (Deep learning, Theoretical )
ویژگی پلی لیست:
Deep Learning from the Foundations, Introduction to Machine Learning for Coders, Practical Deep Learning for Coders

8- Rasa ( Content about: Rasa, AI, NLP )
ویژگی پلی لیست:
NLP for Developers, Developing Contextual AI assistants with Rasa tools, Algorithm Whiteboard, Live Coding

9- Yannic Kilcher ( Content about: NLP, Machine learning, Deep learning, Theoretical )
ویژگی پلی لیست:
NLP, General Machine Learning, Deep Learning Architectures, CV, Applications of Machine Learning

10- OpenAI ( Content about: NLP, Machine learning, AI )
ویژگی پلی لیست:
Events and Talks, Research Releases, Robotics

11- Two Minute Papers ( Content about: Machine Learning and AI Research, Scientific Papers )
ویژگی پلی لیست:
Two Minute Papers, AlphaGo, Fluid, Cloth and Hair Simulations, AI and Deep Learning, Light Transport, Ray Tracing and Global Illumination

12- Machine Learnia ( Content about: Machine Learning, Scikit Learn, Python )
ویژگی پلی لیست:
Deep Learning, SKLEARN tutoriel français Machine Learning, Python Special Machine Learning

13- Mark Saroufim ( Content about: Machine Learning Engineering, Practical videos, Books review )
ویژگی پلی لیست:
Machine Learning Systems, GNN ,...

14- sentdex ( Content about: Python for AI and Finance )
ویژگی پلی لیست:
Python Programming for Finance, Machine Learning with Python, Neural Networks from Scratch in Python

#منابع #مبتدی #مقدماتی #پیشرفته #پایتون #الگوریتمها #هوش_هوصنوعی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

مزایا و معایت الگوریتم های #یادگیری_ماشین

#الگوریتمها #منابع

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

استاد بزرگ Andrej Karpathy مدل LLAMA3.1 8B رو با حداقل منابع فاین تیون کرده

https://github.com/karpathy/nano-llama31

#هوش_مصنوعی #منابع #الگوریتمها

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person