QooryBeta
Neuron

Neuron

0 projects

NRN 正在构建一个生态系统,通过将游戏和机器人作为试验平台,加速向通用人工智能(AGI)的进展。该平台将 AI 代理集成到创新的游戏体验中,并在模拟中训练具身智能,然后部署到实体机器人中。

Projects
0

新闻

“We found that a single neuron can solve MNIST.” Konrad Kording's lab built a computational model of a single neuron that can recognize handwritten numbers — a hint that neurons can do more than we assumed. Full conversation on the @JuanBenet Podcast >>> https://t.co/uLosnelLsr https://t.

@protocollabs2026年7月

You're asking the right question of the wrong science. It really did help me to study Theory of Mind and Epigentics more than Neuroscience. Computational models are super helpful too. But yeah there are a lot of gaps/missing-layers. Now we do have full neuron maps of insects though.

@afdudley02026年6月

I animated how a neural network learns, from one neuron to backpropagation, simple math, no calculus required. Best 8 minutes you can spend if it has only ever been a black box to you.

@tetsuoai2026年6月

The entire core of a neural network on four cards. Neuron, forward pass, activations, backprop. Learn these four and you understand how every model from a perceptron to a transformer predicts and learns.

@tetsuoai2026年6月

What can a neuron compute? Real biological neurons are complex, but how capable are they? Using a new method, we found that a single cortical neuron can classify cats vs dogs, recognize spoken words, and solve 10-bit parity, all tasks thought to require entire networks. (1/15)

@chainyoda2026年6月

RT @IdoAizenbud: What can a neuron compute? Real biological neurons are complex, but how capable are they? Using a new method, we found t…

@MartinShkreli2026年6月

The neuron. weighted sums, a bias, a nonlinear bend.

@tetsuoai2026年6月

I would dispute that. If you simulated every single neuron of Jules Caesar precisely, Jules Caesar to the best of our understanding would be conscious. There's no law of physics that explain why the substrate would matter, and if consciousness goes beyond physics then the physical substrate definit

@arthurb2026年6月

The neuron. weighted sums, a bias, a nonlinear bend.

@tetsuoai2026年5月

A single neuron is not intelligent. A single transistor is not intelligent. Yet when billions of them interact and exchange signals according to simple rules, something quite remarkable emerges. We call that phenomenon intelligence.

@kyegomezb2026年5月