@deepdreamstudios0: Мы уже много чего сделали https://t.me/rustypocket #раст #юнити #растмобайл #rustmobile #fyp

DeepDream Studios

Open In TikTok:

Region: PL

Saturday 02 May 2026 20:17:29 GMT

3823

92

46

3

Music

Download

No Watermark .mp4 (0.38MB) No Watermark(HD) .mp4 (0.38MB) Watermark .mp4 (0MB) Music .mp3

Comments

зов потужно :

а чо по характерістекам

2026-06-20 16:08:41

0

𝕾𝕬𝕸𝕸𝖄 | raspadsquad :

надеюсь он бесплатный и для слабых пк будет?

2026-05-03 14:21:43

8

stantersky72 :

бро ты можешь сделать сервера бателфилд пж?

2026-06-08 18:51:39

0

Evil Morty :

жаль что команда рассталась

2026-06-01 16:21:38

0

 :

фига бро удачи

2026-05-02 20:19:59

2

Rilback :

и все держится на одном ПК локально

2026-05-25 03:45:56

0

STRIT DERT :

добавь меня в збт🙏

2026-05-03 04:37:06

2

◕₣ℜøźєη•M̷O̷N̷S̷T̷E̷R̷◕ :

Сделайте на айфоны и андройды если не будет на телефоны то никто играть не будет

2026-05-09 19:30:50

0

Jve2n :

ого

2026-05-02 21:07:33

1

dochtur :

бро мой совет ч посмотрел как ты сделал инвентарь очень ущербно знаешь он как будто чутка сжатый и цифры слишком большие поработай над этим и камень поменяй чутка а то слишком большой какой-то а так в целом норм

2026-06-02 20:57:14

0

Yashka :

и это еще на юнити

2026-05-30 14:07:52

0

. :

это на телефон тоже пойдёт ?

2026-05-07 19:46:19

0

abcdefghijklmnopqrsruvwxyz :

будет на андроид и аффон

2026-05-09 14:36:30

1

我們需要採取行動。 :

кагда закончите

2026-05-03 21:29:58

0

тони орех ✅ (Z🪓) :

если это выйдет, это будет имбой

2026-05-02 23:11:52

2

vmx root :

если популярная будет то чит сделаем с коммандой

2026-05-20 18:58:50

0

Pisuncheks :

ссылка нерабочая

2026-05-24 10:49:30

0

jefery2282 :

бурст джобы юзаете для патхфинда ботов? как процедурка карты работает? стрельба реем или проджекайлами?

2026-05-28 08:07:53

0

SABLEY :

сколько стоит збт

2026-05-07 10:42:13

0

ChiChi :

https://t.me//rustypocket

2026-06-19 18:28:04

0

Tokyo🥐 :

имба бро не сдавайся и копия будет ебанутой сделай збт за 300 р и донат скины по 500-1000 и ты окупишь сервера и труд

2026-09-24 17:28:50

0

чозабретто :

🥰

2026-05-04 04:31:20

0

To see more videos from user @deepdreamstudios0, please go to the Tikwm homepage.

Other Videos

#mensfashion #vintagefashion #fallfashioninspo #mensfashiontrends #streetwear

#mensfashion #vintagefashion #fallfashioninspo #mensfashiontrends #streetwear

ranking viral chicken screms🐔#chickenscream#viralvideotiktok#fyyyp

ranking viral chicken screms🐔#chickenscream#viralvideotiktok#fyyyp

Ya Mudeer #shaziii_007 #shaziimalik #fyp

Ya Mudeer #shaziii_007 #shaziimalik #fyp

➡️ Part 9 of learning ML code from scratch Six weights, one wrong answer, and not one of them knows it was at fault. Backpropagation is how they find out. Two questions guide the video: what even is backpropagation, and why do models need it? Step 1, the forward pass. Two numbers go into a tiny network, run through a hidden layer, and one number comes out. Ours says 0.700. We wanted 1.0, so square the difference and the loss is 0.09. That single number is how wrong the model is. Step 2, the question. Six weights produced that answer together. Which of them is to blame, and by how much? Step 3, the one idea. Change a single weight by a tiny amount and watch the error move. How much the error changes per unit of weight is the gradient of that weight. In the video you can see it happen: the weight wobbles and the error bar answers. Step 4, the shortcut. Every weight running into the same neuron starts from one shared number, the blame of that neuron. Multiply that blame by the value each weight carried and you have its gradient. One blame, computed once, and every weight into that neuron gets its own gradient from it. That is why backpropagation is fast enough to train anything at all. Step 5, backwards. The blame starts at the output and every layer hands its share to the layer in front of it, back through the same network the data came forward through. It goes layer by layer, and inside one layer every neuron is done together. Step 6, the update. The optimizer moves every weight against its own gradient, the whole weight matrix in one go, so no weight waits for its turn. All six gradients here are negative, so all six weights go up. After one step the answer reads 0.769. After sixty it reads 0.968 and the error is down to 0.001. The honest part: every gradient in the video was checked against the measured change of the error. Move that one weight, see what the error does, divide. Backprop and the measurement agree to nine decimal places, otherwise nothing would have rendered. #machinelearning #backpropagation #neuralnetworks #python #coding

➡️ Part 9 of learning ML code from scratch Six weights, one wrong answer, and not one of them knows it was at fault. Backpropagation is how they find out. Two questions guide the video: what even is backpropagation, and why do models need it? Step 1, the forward pass. Two numbers go into a tiny network, run through a hidden layer, and one number comes out. Ours says 0.700. We wanted 1.0, so square the difference and the loss is 0.09. That single number is how wrong the model is. Step 2, the question. Six weights produced that answer together. Which of them is to blame, and by how much? Step 3, the one idea. Change a single weight by a tiny amount and watch the error move. How much the error changes per unit of weight is the gradient of that weight. In the video you can see it happen: the weight wobbles and the error bar answers. Step 4, the shortcut. Every weight running into the same neuron starts from one shared number, the blame of that neuron. Multiply that blame by the value each weight carried and you have its gradient. One blame, computed once, and every weight into that neuron gets its own gradient from it. That is why backpropagation is fast enough to train anything at all. Step 5, backwards. The blame starts at the output and every layer hands its share to the layer in front of it, back through the same network the data came forward through. It goes layer by layer, and inside one layer every neuron is done together. Step 6, the update. The optimizer moves every weight against its own gradient, the whole weight matrix in one go, so no weight waits for its turn. All six gradients here are negative, so all six weights go up. After one step the answer reads 0.769. After sixty it reads 0.968 and the error is down to 0.001. The honest part: every gradient in the video was checked against the measured change of the error. Move that one weight, see what the error does, divide. Backprop and the measurement agree to nine decimal places, otherwise nothing would have rendered. #machinelearning #backpropagation #neuralnetworks #python #coding

About

Robot
API

Legal

Privacy Policy