#deeplearningjs 搜尋結果

If you want to learn Deep Learning from the ground up to advanced techniques, this open resource is a gem. Full notebook suite -> Link in comments

Say hello to DINOv3 🦖🦖🦖 A major release that raises the bar of self-supervised vision foundation models. With stunning high-resolution dense features, it’s a game-changer for vision tasks! We scaled model size and training data, but here's what makes it special 👇

You’re in an ML Engineer interview at Stripe. The interviewer asks: "People often dispute transactions they actually made. How to build a supervised model that predicts fake disputes? There’s no labeled data." You: "I'll flag cards with high dispute rates." Interview over.…

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters…

Open Deep Search (ODS) is one of @SentientAGI’s signature contributions to the GRID. ODS wraps around any LLM and plugs in a two part system: the Open Search Tool and the Open Reasoning Agent. Together they tackle multi source questions by rephrasing queries, extracting and…

SWE-grep is truly some inspired ML from @cognition. Take a 1M line codebase like React. With multiple fast inference calls on Cerebras, it can fetch & explain relevant code in seconds. Here are a few measurements taken on React, Vercel, PyTorch repos.

Congrats to @deepseek_ai ! DeepSeek-R1 was published in Nature yesterday as the cover article, and vLLM is proud to have supported its RL training and inference🥰

DeepSeek V3 is a popular Large-Language Model that's a good one to know if you're interested in AI. And in this course, you'll learn how it works. It covers DeepSeek's Multi-Head Latent Attention mechanism, Mixture of Experts architecture, and lots more.…

A Randomized Controlled Trial of a Deep Language Learning Model‑Based Simulation Tool for Undergraduate Medical Students in Surgery #ChatGPT #AI #MedicalEducation #AIMedEd #MedicalSimulation #MedTwitter #SimMed #FutureOfMedicine #AIinHealthcare pubmed.ncbi.nlm.nih.gov/40729832/

I'm deleting this in 24hrs because it's a legit formula to PRINT CASH. DeepSeek Prompts Cheatsheet You can make THOUSANDS building and selling them, and literally anyone can do it. Comment "DS" and I will DM you my full 23-hour video course right now! (must follow)

Introducing DeepConf: Deep Think with Confidence 🚀 First method to achieve 99.9% on AIME 2025 with open-source models! Using GPT-OSS-120B even without tools, we reached this almost-perfect accuracy while saving up to 85% generated tokens. It also delivers many strong…

ChatGPT is so advanced now. I needed to find the differential nonlinear error of this DAC board i designed and was using a nanovoltmeter. stepping though DAC codes up to 10V lowers the # of digits you can see on the voltmeter so i was stumped on how i could see a reading << 1 DAC…

deep learning is just a higher order math. > this book breaks down the linear algebra, calculus, and probability that make neural networks actually work. > perfect for engineers and learners who want to understand, not just copy code

1/ DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning This changes everything: Researchers are teaching large language models to develop independent, deep thinking - without humans dictating every single step of the thought process. A game changer for AI…

New in the @medusajs docs: enable deep thinking in our AI assistant to get better answers for more complex questions. Powered by @kapa_ai Try it out -> docs.medusajs.com

I've released my course on deep learning for computer vision! It includes slides, google colab, and Anki decks for all 6 topics I'm covering. We code from the basics (backprop from scratch) to the SotA (transformers & MLP-mixer). arthurdouillard.com/deepcourse/ Feedback appreciated!

Peer reviewed version of Deepseek R1 paper in Nature. Hard to believe it's only been 9 months since R1 - seems like a lifetime ago! "The paper updates a preprint released in January, which describes how DeepSeek augmented a standard large language model (LLM) to tackle…

timelapse {#8} > week 3 assignment > sigmoid activation from scratch > tanh activation from scratch > single layer neural network from scratch

Jevons' paradox in LLMs: Deep Research mode always on chatgpt.com/s/dr_68f295826…