Neural Black Magic
رفتن به کانال در Telegram
Learn the latest trends in Machine Learning and Deep Learning; Learn the black magic of AI with me. Watch us on YouTube📽: https://youtube.com/@NeuralBlackMagic Read our Blogposts on Medium📃: https://medium.com/@NeuralBlackMa DM📨: @ardawanism
نمایش بیشتر396
مشترکین
اطلاعاتی وجود ندارد24 ساعت
+97 روز
+1230 روز
در حال بارگیری داده...
کانالهای مشابه
هیچ دادهای
مشکلی وجود دارد؟ لطفاً صفحه را تازه کنید یا با مدیر پشتیبانی ما تماس بگیرید.
ابر برچسبها
اشارات ورودی و خروجی
---
---
---
---
---
---
جذب مشترکین
آوریل '25
آوریل '250
در 0 کانالها
مارس '25
+24
در 0 کانالها
Get PRO
فوریه '25
+222
در 0 کانالها
Get PRO
ژانویه '250
در 0 کانالها
Get PRO
دسامبر '240
در 0 کانالها
Get PRO
نوامبر '24
+94
در 0 کانالها
Get PRO
اکتبر '240
در 1 کانالها
Get PRO
سپتامبر '24
+4
در 0 کانالها
Get PRO
اوت '240
در 0 کانالها
Get PRO
ژوئیه '24
+5
در 0 کانالها
Get PRO
ژوئن '240
در 0 کانالها
Get PRO
مه '240
در 0 کانالها
Get PRO
آوریل '24
+70
در 0 کانالها
| تاریخ | رشد مشترکین | اشارات | کانالها | |
| 01 آوریل | 0 |
پستهای کانال
| 2 |  AI Agentic Design Patterns with AutoGen
By DeepLearning.AI
@neuralblackmagic | 344 |
| 3 |  تیم InceptionLabs اولین خانواده تجاری از مدلهای زبانی مبتنی بر فرایند انتشار یا
Diffusion Large Language Models (dLLMs)
به نام "Mercury" رو معرفی کرده.
این مدلها پنج تا ده برابر سریعتر و ارزانتر از مدلهای زبانی Autoregressive فعلی هست. مدلهای زبانی مبتنی بر انتشار برخلاف مدلهای Autoregressive که توکن به توکن به تولید متن میپردازند با رویکرد coarse-to-fine به تولید همزمان کل متن از یک نویز اولیه میپردازند.
در این لینک میتونید بیشتر درباره "Mercury" بخونید.
مدل Mercury Coder، یک dLLM بهینه شده برای تولید کد، به صورت عمومی در دسترس قرار گرفتهاست. برای امتحان مدل میتونید از طریق Playground اقدام کنید.
امتحانش کنید 🤩؛ واقعا سریع هست 🔥.
@neuralblackmagic | 690 |
| 4 |  🤖📚 The Hundred-Page Language Models Book
by Andryi Burkov.
👨🏼🏫 Who Is Andryi Burkov?
Andriy Burkov holds a Ph.D. in Artificial Intelligence. He works as a senior data scientist and machine learning team leader at TalentNeuron [1, 2].
📝 Table of Contents:
● Machine Learning Basics
● Language Modeling Basics
● Recurrent Neural Networks (RNNs)
● Transformer
● Large Language Models
● Further Reading
○ Mixture of Experts
○ Model Merging
○ Model Compression
○ Preference-based Alignment
○ Advanced Reasoning
○ LM Security
○ Vision-Language Models
○ Preventing Overfitting
Read The Book:
https://www.thelmbook.com/
https://github.com/aburkov/theLMbook
Share with your friends too 😇🤗.
@neuralblackmagic | 457 |
| 5 |  بدون متن... | 1 |
| 6 | 📃 Building Trusted AI In The Enterprise by Anthropic.
Share with your friends too 😇🤗.
@neuralblackmagic | 336 |
| 7 |  🚀 Join Peter Stone’s Talk at Sharif University of Technology
🎙Title: Multiagent RL: Cooperation and Competition
👨🏫 Speaker: Peter Stone (Professor of Computer Science, University of Texas at Austin)
📅 Date: Thursday (Feb 27, 2025)
🕗 Time: 3:30 PM Iran Time
💡Sign Up Here.
📝 Professor Peter Stone recommends that all of you watch his talk at RLC 2024, titled: "Practical Reinforcement Learning: Lessons from 30 Years of Research"
🎥 https://www.youtube.com/watch?v=5Dw4OoJK9Qw
@neuralblackmagic | 344 |
| 8 |  🚀 Join Chris Watkins’s Talk at Sharif University of Technology
🎙 Title: From Shortest Paths to Value Iteration to Q-Learning
👨🏫 Speaker: Chris Watkins (Professor of Computer Science, Royal Holloway)
📅 Date: Friday (Feb 21, 2025)
🕗 Time: 3:00 PM Iran Time
💡 Sign Up Here:
https://forms.gle/ET3Y5jB6Jt9vkQ2x9
@neuralblackmagic | 371 |
| 9 |  Gold 🏆🚀
📝 Table of Contents:
● Introduction
● Notation and Definitions
● Fundamental Algorithms
● Anatomy of a Learning Algorithm
● Basic Practice
● Neural Networks and Deep Learning
● Problems and Solutions
● Advanced Practice
● Unsupervised Learning
● Other Forms of Learning
● Conclusion
Share with your friends too 😇🤗.
Support the channel please 🌱.
@neuralblackmagic | 357 |
| 10 |  🚀 Join Michael Littman’s Talk at Sharif University of Technology
🎙 Title: Assessing the Robustness of Deep RL Algorithms
👨🏫 Speaker: Michael Littman (Brown University, Humanity-Centered Robotics Initiative)
📅 Date: Friday (Feb 21, 2025)
🕗 Time: 5:30 PM Iran Time
💡 Sign Up Here:
https://forms.gle/amgtsGrDVn4mdRai9 | 323 |
| 11 |  امیرمحمد خالقی💔🖤 | 381 |
| 12 |  “Deep Learning with Python”
by François Chollet and Matthew Watson.
François Chollet is a French software engineer and artificial intelligence researcher formerly Senior Staff Engineer at Google. Chollet is the creator of the Keras deep learning library, released in 2015.
Read online here.
Share with your friends 😇🤗.
@neuralblackmagic | 382 |
| 13 | “Deep Learning with Python”
by François Chollet and Matthew Watson.
François Chollet is a French software engineer and artificial intelligence researcher formerly Senior Staff Engineer at Google. Chollet is the creator of the Keras deep learning library, released in 2015.
Read online here. | 1 |
| 14 | 🔉 Missed yesterday's talk by Rich Sutton?
No worries! You can watch the full recording here 🤩:
🎥 https://www.youtube.com/watch?v=Y4UZNc4eh4U
@neuralblackmagic | 2 |
| 15 | 📃 Towards Out-Of-Distribution Generalization: A Survey
📝 Abstract:
Out-of-Distribution (OOD) generalization is an emerging topic of machine learning research that focuses on complex scenarios wherein the distributions of the test data differ from those of the training data. This paper represents the first comprehensive, systematic review of OOD generalization, encompassing a spectrum of aspects from problem definition, methodological development, and evaluation procedures, to the implications and future directions of the field.
Share with your friends😇🤗.
@neuralblackmagic | 411 |
| 16 | 📃 Open-Endedness is Essential for Artificial Superhuman Intelligence
📝 Abstract:
In this position paper, we argue that the ingredients are now in place to achieve open-endedness in AI systems with respect to a human observer. Furthermore, we claim that such open-endedness is an essential property of any artificial superhuman intelligence (ASI). We begin by providing a concrete formal definition of open-endedness through the lens of novelty and learnability. We then illustrate a path towards ASI via open-ended systems built on top of foundation models, capable of making novel, human-relevant discoveries. We conclude by examining the safety implications of generally-capable open-ended AI. We expect that open-ended foundation models will prove to be an increasingly fertile and safety-critical area of research in the near future.
Share with your friends😇🤗.
@neuralblackmagic | 391 |
| 17 | Open_Endedness_is_Essential_for_Artificial_Superhuman_Intelligence.pdf | 6 |
| 18 | 📃 Cheet Sheet for Machine Learning
🔗 Source: https://www.cheatsheets.aqeel-anwar.com
Share with your friends😇🤗.
@neuralblackmagic | 360 |
| 19 |  🚀 Join Richard Sutton’s Talk at Sharif University of Technology
🎙 Title: The Increasing Role of Sensorimotor Experience in Artificial Intelligence
👨🏫 Speaker: Richard Sutton (Keen Technologies, University of Alberta, Openmind Research Institute)
📅 Date: Wednesday
🕗 Time: 8 PM Iran Time
💡 Sign Up Here:
https://forms.gle/q1M7qErWvydFxR9m6 | 1 832 |
| 20 |  Linear Algebra and Optimization with Applications to Machine Learning
Volume I: Linear Algebra for Computer Vision, Robotics, and Machine Learning
Freely download here 🤗.
📝 Table of Contents:
● Introduction
● Vector Spaces, Bases, Linear Maps
● Matrices and Linear Maps
● Haar Bases, Haar Wavelets, Hadamard Matrices
● Direct Sums, Rank-Nullity Theorem, Affine Maps
● Determinants
● Gaussian Elimination, LU-Factorization, Cholesky Factorization, Reduced Row Echelon Form
● Vector Norms and Matrix Norms
● Iterative Methods for Solving Linear Systems
● The Dual Space and Duality
● Euclidean Spaces
● QR-Decomposition for Arbitrary Matrices
● Hermitian Spaces
● Eigenvectors and Eigenvalues
● Spectral Theorems in Euclidean and Hermitian Spaces
● Computing Eigenvalues and Eigenvectors
● Graphs and Graph Laplacians; Basic Facts
● Spectral Graph Drawing
● Singular Value Decomposition and Polar Form
● Applications of SVD and Pseudo-Inverses
Share with your friends😇🤗.
@neuralblackmagic | 421 |
