🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

There is no feeling like coding at late night, fully channelled with a good music in bg. Need to sleep at some point, you don't care.

Learns a new language on forward pass ✨

We have a long history of supporting responsible open source & science, which can drive rapid research progress, so we’re proud to release Gemma: a set of lightweight open models, best-in-class for their size, inspired by the same tech used for Gemini blog.google/technology/dev…

I highly recommend Google TPU Research Cloud Programme to researchers. Those TPUs made our COSYNE'24 work on evolving spiking neuron models possible.

Turning sand into spice.

transformers and gpus won't be the last ones.

Substantial preprint: we explore how adaptive decoders for brain-computer interfaces influence learning in the brain. We mix theory and experiments to uncover how closed-loop error manipulation shapes neural representations in the brain. Useful to probe learning and improve BCI!

.Filippo_Moro Tristan Yigit Melika Payvand et al. present a #Spiking #NeuralNetwork #hardware with #dendritic architecture based on #memristive #devices for low-power signal processing with reduced memory footprint. Now out 👉 Nature Communications nature.com/articles/s4146…

New paper! Happy to share our latest work on implementing dendritic delay computation with analog devices, DenRAM, is now published on Nature Communications!

I am joining Google as Research Scientist starting from June✨ I am deeply inspired by the impact of their fundamental research, and excited for the team's great potential to discover paradigms beyond today.

Using Gemini as a music discovery tool seems to be working surprisingly well Google 😅🎵

Türkiye'deki arkadaşlar için yıllardır kullandığım Proton VPN'i öneriyorum.

There he co-taught a legendary class on "Physics of Computation" with VLSI giant Carver Mead and physics giant Richard Feynman. Don't you wish you could jump in a time machine and take that class? caltech.edu/about/news/cal…

Why does #compneuro need new learning methods? ANN models are usually trained with Gradient Descent (GD), which violates biological realities like Dale’s law and log-normal weights. Here we describe a superior learning algorithm for comp neuro: Exponentiated Gradients (EG)! 1/12

Considering slowly migrating to 🦋 My username is “yigit.ai”

Welcome to the world, Gemini 2.0 ✨ our most capable AI model yet. We're first releasing an experimental version of 2.0 Flash ⚡ It has better performance, new multimodal output, Google tool use - and paves the way for new agentic experiences. 🧵 goo.gle/gemini-2

Twitter used to be my favorite place on the Internet. I've derived enormous value from it in the past 16 years. Not true anymore. Most of the people I enjoyed reading have left. My feed, which used to feature art and science and technology and humor, has become constant

Hey Elon Musk, could you elucidate the reasoning behind X's restricting access to people's accounts engaged in expressing pro-democracy sentiments in Turkey?

Our team is hiring in Zürich! google.com/about/careers/…

Super happy and proud to share our novel scalable RNN model - the MesaNet! This work builds upon beautiful ideas of 𝗹𝗼𝗰𝗮𝗹𝗹𝘆 𝗼𝗽𝘁𝗶𝗺𝗮𝗹 𝘁𝗲𝘀𝘁-𝘁𝗶𝗺𝗲 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 (TTT), and combines ideas of in-context learning, test-time training and mesa-optimization.