Loading video...

Video Failed to Load

Go Home

Hugo Larochelle explains how a neuron computes its output: first, it calculates the preactivation, the sum of the bias and weighted inputs, and then applies an activation function.

29,307 views • 11 months ago •via X (Twitter)

24 Comments

Kuldy Singh's profile picture
Kuldy Singh11 months ago

👌

ljpygl | 100X PVE's profile picture
ljpygl | 100X PVE11 months ago

Macrohard

AlexSGabor's profile picture
AlexSGabor11 months ago

@grok can neurons compute?

Rowan Brad Quni-Gudzinas's profile picture
Rowan Brad Quni-Gudzinas11 months ago

Note: "artificial" neuron, the legacy of the perceptron as adapted for neural networks (AI). I've been thinking about this: There's no way biologic neuronal architecture is serialized like this (too slow), so an updated NN would be parallel (system of equations or quantum)

BobbyWx's profile picture
BobbyWx11 months ago

Trash explanation

Amzad Hossain's profile picture
Amzad Hossain11 months ago

👏👏👏🎯

Selena Maris's profile picture
Selena Maris11 months ago

Hugo Larochelle's neuron explanation? Yawn another ivory-tower egghead regurgitating basic neural net math like it’s divine revelation. Preactivation, weights, bias, activation function? This is undergrad AI 101, not groundbreaking insight. While he’s preaching to the choir, Big Tech’s black-box algorithms built on this oversimplified drivel are fleecing privacy, rigging elections, and automating job theft. Larochelle’s not enlightening us; he’s shilling for the AI overlords, dressing up their dystopian code as "science." Wake up, sheep this neuron worship is just propaganda for the singularity scam!

Lexor's profile picture
Lexor11 months ago

We are amazing computers

Kuldy Singh's profile picture
Kuldy Singh11 months ago

👌

☄️'s profile picture
☄️11 months ago

Neurons out here doing math while we struggle to remember our PINs. 😅🧠

Leonardo Granizo 🤓🧠's profile picture
Leonardo Granizo 🤓🧠11 months ago

Pure Maths 😎 the oldest Science

☄️'s profile picture
☄️11 months ago

Hugo Larochelle breaks it down simply — preactivation plus activation function equals neuron output. 👀✨

SigmaXyzwmxn Complexdynamics's profile picture
SigmaXyzwmxn Complexdynamics11 months ago

Elegant

☄️'s profile picture
☄️11 months ago

Neurons: “We sum, we activate, we conquer.” Humans: still can’t calculate a tip. 😏💡

Leon's profile picture
Leon11 months ago

Lol. It's complicated as hell, but it's fun to learn.

michael's profile picture
michael11 months ago

So simple at the heart of it.

R's profile picture
R11 months ago

3blue1brown has some very beautiful videos on this god I wish I were 18 again so I could study this stuff instead of the boring crap I do

Stanley Wei's profile picture
Stanley Wei11 months ago

Thanks for sharing. Planning on making a neural network soon?

Jake's profile picture
Jake11 months ago

@grok explain better

eigentiki's profile picture
eigentiki11 months ago

~ thanks for this clip slatt!

Kangaro0_🦘's profile picture
Kangaro0_🦘11 months ago

@grok what is being explained. I’m lost. Explain it to me like I missed this class

Irving Salinas's profile picture
Irving Salinas11 months ago

I remember when I was studying at the university about this in a AI course at 2010, we make a neuron with OpAmps (electronics) and We was entry a lot of signals for watch your results. Today the AI is an reality!

𝑉𝑖𝑘!'s profile picture
𝑉𝑖𝑘!11 months ago

@grok ¿Qué tipo de persona entiende esto, un matemático o un programador?

☄️'s profile picture
☄️11 months ago

When a neuron casually does complex math every millisecond and you’re like… 💀🤯

Related Videos