Understanding Deep Learning — 541-page PDF eBook and 68 coding exercises with Python code notebooks that cover all the topics in the book: http://
udlbook.github.io/udlbook/ …or buy the book here: http://
amzn.to/4qwof9k
RESEARCH
-

Understanding Deep Learning — 541‑page eBook and Code Notebooks
By
–
-

Mathematical Theory of Deep Learning — arXiv Paper and Book
By
–
Mathematical Theory of #DeepLearning [download 333-page PDF]: http://
arxiv.org/abs/2407.18384 *UPDATED*
+ +
See also this book: http://
amzn.to/3BqaW5e
—————
#AI #DataScience #ML #MachineLearning #Calculus #DataScientist #Mathematics #Algorithms -
AI Video Generation Enters New Dimension with Higgsfield x Kling 3.0
By
–
Ce n’est pas une simple évolution.
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 5 février 2026
C’est un changement de règle.
Higgsfield × Kling 3.0 fait entrer la vidéo IA dans une autre dimension.
⁰Séquences multi-plans. Audio natif.
Cohérence totale des personnages.⁰15 secondes de génération continue sans hacks, sans rafistolage.… https://t.co/Gge6ievNUh pic.twitter.com/hGWXPGigW2Ce n’est pas une simple évolution. C’est un changement de règle. Higgsfield × Kling 3.0 fait entrer la vidéo IA dans une autre dimension.
Séquences multi-plans. Audio natif. Cohérence totale des personnages. 15 secondes de génération continue sans hacks, sans rafistolage. -
RLHF Bias: Millions for Nice but Useless Answers
By
–
They are working on it; the problem is that they paid millions of dollars, notably OpenAI, to get RLHF databases where labelers tended to choose nice answers rather than useful ones. Whether it's human bias or a directive, we don't know, but it's been identified….
-
Hybrid TCN-Attention Model Advances Industrial Predictive Maintenance
By
–
Our novel hybrid deep learning model (TCN-Attention) for predictive maintenance outperforms current methods (Expert Systems with Applications). Enhances failure prediction & interpretability for critical industrial systems. @faustospain @Isaac_Segovia_ sciencedirect.com/science/ar…
→ View original post on X — @faustospain, 2026-02-05 09:58 UTC
-
Wayve CEO discusses AI-driven autonomous driving approach on podcast
By
–
Autonomy isn’t just about more data or more compute – it’s about learning efficiently. Our CEO @alexgkendall joined the #TechCarsMachines podcast with @alitab99 to discuss Wayve’s AI-driven, end-to-end approach to autonomous driving. Listen here; gtkpartners.com/wayve #Podcast #Autonomy #AVs
→ View original post on X — @ryan_browne_, 2026-02-05 07:00 UTC
-
Real-time world model generation from text and image prompts
By
–
In our research lab, we are building “real-time dreaming” – the ability to generate fully playable video worlds prompted from any text or image.
— Roblox (@Roblox) 5 février 2026
Our real-time, action conditioned world model (currently running internally at 16fps at 832x480p) is trained on a combination of data,… pic.twitter.com/R5CKJkFuh2In our research lab, we are building “real-time dreaming” – the ability to generate fully playable video worlds prompted from any text or image. Our real-time, action conditioned world model (currently running internally at 16fps at 832x480p) is trained on a combination of data, including proprietary Roblox 3D avatar/world interaction data. World models are different from multiplayer engines in that they store state and memory in video latents. Roblox is multiplayer, and we are actively researching optimal ways to simultaneously store state for thousands of players, and keep them in sync with their environment. Our world model leverages database technology which stores all user interactions on Roblox in a vector format that can be used to re-render video and interaction from any camera angle. We see several immediate uses for our Roblox world model. We will use it side-by-side text, image and video prompts as a way to launch auto-generation of immersive worlds. In Roblox Studio, a creator could walk around and use prompts to “paint” a world and then convert it into a 3D representation or direct to Roblox native as a way for many people to play simultaneously. All of this comes alive as we explore the notion of a “Dream Theater” – where one user is dreaming, while others watch and prompt them. 2/4 Community note: The beginning of the video has stolen assets/design from Clair Obscur: Expedition 33 by Sandfall Interactive. The environment is the Flying Waters area and the girl in the video is Maelle. store.steampowered.com/app/1903340/Cl… expedition33.wiki.fextralife.com/Flying+Waters clair-obscur.fandom.com/wiki/Maelle
→ View original post on X — @shiqi_yang_147, 2026-02-05 01:28 UTC
-

NVIDIA and Dassault Systèmes Blueprint Industrial AI World Models
By
–
This is the largest collaboration our two companies have ever had in over a quarter century.” Jensen Huang. At #3DXW26, @Dassault3DS and NVIDIA laid out a blueprint for industrial AI rooted in physics-based “world models” — systems designed to simulate products, factories and
-
McCarthy’s Symbolic Systems Versus Connectionist AI Approaches
By
–
Fair, this is a good and helpful note, thank you. McCarthy himself was focused on symbolic systems, and skeptical of the connectivist/ McCullouch & Pitts schools, is a more precise way of making the point I meant to make.
-
Tinker Community Achievements: Models, Infrastructure, Research Roundups
By
–
Since Tinker launched, our community has used it to train state-of-the-art models, build infrastructure, and publish novel research. We will be highlighting this creative work in regular roundups, and hope to inspire your own Tinkering as well.
→ View original post on X — @soumithchintala, 2026-02-04 21:14 UTC