Erkan Oğuz

GPT-4o is now available in the API. It’s as smart as GPT-4 Turbo, has improved vision capabilities, and is much more efficient—2x faster, 50% cheaper, 5x rate limits. It supports text and vision today, with audio and video coming soon. Details in thread 🧵 openai.com/index/hello-gp…

🇹🇷 FİLENİN SULTANLARI AVRUPA ŞAMPİYONU! 🥇 En sert blokları azminiz ve inancınızla aştınız. Bu büyük sevinci tüm Türkiye'ye yaşattınız! 😍 Bu zafer adanmışlığın zaferidir! 💪 TEBRİKLER SULTANLAR! 👏

!!!! Ok I recorded a (new!) 2h25m lecture on "The spelled-out intro to neural networks and backpropagation: building micrograd" youtube.com/watch?v=VMj-3S… . This is the culmination of about 8 years of obsessing about the best way to explain neural nets and backprop.

code::dive conference 2014 - Scott Meyers: Cpu Caches and Why You Care youtu.be/WDIkqP4JbkE @YouTube aracılığıyla

🔺

How to evaluate your ML model? 📏 Your accuracy is 97%, so this is pretty good, right? Right? No! ❌ Just looking at the model accuracy is not enough. Let me tell you about some other metrics: ▪️ Recall ▪️ Precision ▪️ F1 score ▪️ Confusion matrix Let's start 👇

I wrote an article about bitcoin's scaling pattern and energy usage: swanbitcoin.com/bitcoins-energ…

💯 CS 251 Intermediate Software Design: Course Overview and Logistics youtu.be/LTE6BWfjOUo @YouTube aracılığıyla

Bitcoin mining is really bad for the environme twitter.com/CosmosDoctor2/…

One of my favorite slides from Track 1 from none other than @nic_carter. Bitcoin consumes less energy than domestic tumble driers. Don't @ me.

Proof of Work vs Proof of Stake

#NSFirstHumanFlight live broadcast hosted by Ariane Cornell starts now on BlueOrigin.com.

covariance vs. mutual information

Learn about modern speech recognition and the Graph Transformer Networks with @awnihannun! In this lecture, Awni covers the connectionist temporal classification (CTC) loss, beam search decoding, weighted finite-state automata and transducers, and GTNs! youtu.be/Of9s8epjflU

Gave a talk at CVPR over the weekend on our recent work at Tesla Autopilot to estimate very accurate depth, velocity, acceleration with neural nets from vision. Necessary ingredients include: 1M car fleet data engine, strong AI team and a Supercomputer youtu.be/eOL_rCK59ZI?t=…

We’re sharing significantly improved Mask R-CNN baselines that match recent SOTA results from other #computervision experts. We’re also providing an analysis of what drove these gains & adding recipes to our open source Detectron2 object detection library. ai.facebook.com/blog/advancing…

Everything you want (or need) to know about self-supervised learning for vision in this interview of FAIR's Ishan Misra with ML Street Talk.