Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Trained a single layer neural network in C to predict AND GATE from scratch using gradient descent and Batch training of dataset in almost 300K epochs

AADITYANSHA

2,109 subscribers

81,439 görüntüleme • 7 ay önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

28 Yorum

Athrix ☄️ profil fotoğrafı

Athrix ☄️7 ay önce

Noicee

Harsh Jain profil fotoğrafı

Harsh Jain7 ay önce

Crazy buddy 🥶

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

@HarshJain_Coder Thnx

Humi profil fotoğrafı

Humi7 ay önce

oohh cooooll

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

Thnx

Zerion profil fotoğrafı

Zerion7 ay önce

Woo super cool bhai

Tħ∀TΣΔGIC∀LCΔT profil fotoğrafı

Tħ∀TΣΔGIC∀LCΔT7 ay önce

cool! this is pretty nostalgic, i made a little neutral network library and predicted xor gate as an example. @DuskyDaily made a pr and that's how we met!

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

@DuskyDaily Xor gate, nice bro Pls do share me the library Btw did u used mean square error method or something else for error optimization

Tħ∀TΣΔGIC∀LCΔT profil fotoğrafı

Tħ∀TΣΔGIC∀LCΔT7 ay önce

@DuskyDaily mean squared error if I remember correctly

Yosefu profil fotoğrafı

Yosefu7 ay önce

Right what I needed to see Thank you

akansha profil fotoğrafı

akansha7 ay önce

damnn cool

Ruchira profil fotoğrafı

Ruchira7 ay önce

Lesgoooo

Manvi✨ profil fotoğrafı

Manvi✨7 ay önce

Cool

kushzz profil fotoğrafı

kushzz7 ay önce

How tf did u run 300k epochs ?? how long did it take to complete that ??

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

45 sec

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

I'm on i3 2nd gen Pls show some mercy

Sharav Arora profil fotoğrafı

Sharav Arora6 ay önce

superbb

Armandeep Singh Bains profil fotoğrafı

Armandeep Singh Bains5 ay önce

Kindly check your dm.

Apoorva profil fotoğrafı

Apoorva7 ay önce

Keep going buddy like this

PsychoBunny ⚒️ profil fotoğrafı

PsychoBunny ⚒️5 ay önce

Cool, I will try to do the same but with ReLU and the nonlinear gradient descent algorithm.

silicognition profil fotoğrafı

silicognition7 ay önce

@clumsyaf222 cuda or cpu?

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

@clumsyaf222 i3 2nd gen Dual core processor Forgive me for not having a good processor

Kushagra profil fotoğrafı

Kushagra7 ay önce

Insane brother. Now predict XOR gate

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

Yes

Devster profil fotoğrafı

Devster7 ay önce

damw it's is soo cool

sonu profil fotoğrafı

sonu7 ay önce

Which GPU you have for run 300K epochs 🫨

AADITYANSHA profil fotoğrafı

AADITYANSHA7 ay önce

i3 2nd gen Intel processor 🤣

sonu profil fotoğrafı

sonu7 ay önce

Not possible 😂

Benzer Videolar

Andrej Karpathy summarizes how neural networks function, including the process of using a loss function in training and applying backpropagation for optimizing the network parameters through gradient descent.

Andrej Karpathy summarizes how neural networks function, including the process of using a loss function in training and applying backpropagation for optimizing the network parameters through gradient descent.

tetsuo

142,508 görüntüleme • 1 yıl önce

A 2-layer neural network goes from total chaos to perfectly separating left vs right classes in real time. Watch the decision boundary form live as gradient descent works its magic! Pure maths beauty in motion..

A 2-layer neural network goes from total chaos to perfectly separating left vs right classes in real time. Watch the decision boundary form live as gradient descent works its magic! Pure maths beauty in motion..

Mathematica

145,285 görüntüleme • 8 ay önce

I built a neural network inference engine from scratch in ~100 lines of C++. Here I explain it simply.

I built a neural network inference engine from scratch in ~100 lines of C++. Here I explain it simply.

ninjaHattori1

146,820 görüntüleme • 2 ay önce

I was bored, so I created a self-learning Flappy Bird from scratch using a neural network and a genetic algorithm.

I was bored, so I created a self-learning Flappy Bird from scratch using a neural network and a genetic algorithm.

Tanay🔳

4,497,099 görüntüleme • 1 yıl önce

Trickshot vs Neural Bot | Toroidal World | Graphwar Bots Gradient Descent Bot is now Neural Bot Neural Bot: trains a small neural network live on screen every tum, with the enemies as its training data, and fires the curve it learns as its shot. #simulation #graphwar #math #neuralnetwork

Trickshot vs Neural Bot | Toroidal World | Graphwar Bots Gradient Descent Bot is now Neural Bot Neural Bot: trains a small neural network live on screen every tum, with the enemies as its training data, and fires the curve it learns as its shot. #simulation #graphwar #math #neuralnetwork

OnionDas (Science Loop)

50,800 görüntüleme • 6 gün önce

Implemented a visualization for the neural network today. This is a neural network being trained to learn the snake game in a terminal. It's built in Rust using Ratatui More input details in thread

Implemented a visualization for the neural network today. This is a neural network being trained to learn the snake game in a terminal. It's built in Rust using Ratatui More input details in thread

Bones

165,760 görüntüleme • 2 yıl önce

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

109,764 görüntüleme • 1 yıl önce

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

117,748 görüntüleme • 1 yıl önce

I vibecoded this neural network visualization for my students and open sourced it. It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using Three.js and it comes with training code in PyTorch . Link + repo 👇

I vibecoded this neural network visualization for my students and open sourced it. It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using Three.js and it comes with training code in PyTorch . Link + repo 👇

David Finsterwalder | 🇪🇺/acc

488,596 görüntüleme • 1 yıl önce

Canadian engineers have created a robot that is almost impossible to beat in a puck game For a year and a half, it was trained in simulations — it played thousands of virtual matches and learned to predict the puck’s trajectory, taking into account bounces off the boards and tiny surface irregularities. To do this, a separate neural network was trained specifically to calculate the physics of impacts. Now the robot reacts faster than a human and simultaneously keeps multiple possible puck movements in mind.

Canadian engineers have created a robot that is almost impossible to beat in a puck game For a year and a half, it was trained in simulations — it played thousands of virtual matches and learned to predict the puck’s trajectory, taking into account bounces off the boards and tiny surface irregularities. To do this, a separate neural network was trained specifically to calculate the physics of impacts. Now the robot reacts faster than a human and simultaneously keeps multiple possible puck movements in mind.

NEXTA

179,326 görüntüleme • 4 ay önce

Trained a small neural network in Verse to play Snake #UEFN #CreatedInFortnite #Verse

Trained a small neural network in Verse to play Snake #UEFN #CreatedInFortnite #Verse

Julianxd

12,769 görüntüleme • 5 ay önce

Mnist neural network visualization written from scratch in Odin and Raylib. repo: I'm still new to Odin so if you see a way to imporve something, let me know :)

Mnist neural network visualization written from scratch in Odin and Raylib. repo: I'm still new to Odin so if you see a way to imporve something, let me know :)

Bones

97,798 görüntüleme • 2 yıl önce

Created liquid metal effect using CSS and JS from our Figma tutorial. 7 layers of radial gradient with "difference" blend mode. Animated with framer-motion by changing gradient spread and rotation of a base layer. Reply in the comments or DM to get a link to the code.

Created liquid metal effect using CSS and JS from our Figma tutorial. 7 layers of radial gradient with "difference" blend mode. Animated with framer-motion by changing gradient spread and rotation of a base layer. Reply in the comments or DM to get a link to the code.

Alex Barashkov

34,741 görüntüleme • 2 yıl önce

Watch Spot crouch, jump, climb boxes and leap across gaps, controlled by a neural network trained with reinforcement learning (RL) and multi-expert distillation. Multiple expert policies were trained and distilled together into a single policy that was fine tuned to improve performance over diverse terrains. This work was inspired by ANYmal’s parkour capabilities. The neural network processes depth data from Spot's sensors to construct an understanding of the environment.

Watch Spot crouch, jump, climb boxes and leap across gaps, controlled by a neural network trained with reinforcement learning (RL) and multi-expert distillation. Multiple expert policies were trained and distilled together into a single policy that was fine tuned to improve performance over diverse terrains. This work was inspired by ANYmal’s parkour capabilities. The neural network processes depth data from Spot's sensors to construct an understanding of the environment.

RAI Institute

15,150 görüntüleme • 6 ay önce

wrote a piece on how we do tiling and gradient descent on TinyTPU included some animations of the weight and bias gradient descent

wrote a piece on how we do tiling and gradient descent on TinyTPU included some animations of the weight and bias gradient descent

Xander Chin

33,195 görüntüleme • 1 yıl önce

I trained a neural network to mimic a forest trail near my apartment (web demo in the post)

I trained a neural network to mimic a forest trail near my apartment (web demo in the post)

Ollin Boer Bohan

118,477 görüntüleme • 1 yıl önce

With Helix 02, Figure has introduced a new foundational layer for whole-body control that replaces 109k lines of hand-engineered C++ with a single neural prior for stable, natural motion. - Learned from 1,000+ hours of human motion data and sim-to-real RL across 200,000+ parallel environments. - A 10M-parameter neural network that takes full-body joint state and base motion as input and outputs joint-level actuator commands at 1 kHz (1,000 times a second).

With Helix 02, Figure has introduced a new foundational layer for whole-body control that replaces 109k lines of hand-engineered C++ with a single neural prior for stable, natural motion. - Learned from 1,000+ hours of human motion data and sim-to-real RL across 200,000+ parallel environments. - A 10M-parameter neural network that takes full-body joint state and base motion as input and outputs joint-level actuator commands at 1 kHz (1,000 times a second).

The Humanoid Hub

28,004 görüntüleme • 9 ay önce

I'm making a game from scratch in C and getting it shipped to Steam in 90 days. I'm also recording every single step of the process to share with ya. The whole thing is 100% free in ->

I'm making a game from scratch in C and getting it shipped to Steam in 90 days. I'm also recording every single step of the process to share with ya. The whole thing is 100% free in ->

randy

6,398,007 görüntüleme • 2 yıl önce

Motion planning in complex tasks is hard and still done via slow, explicit, traditional planners. We present a generalist Neural Motion Planner -- a single neural network that plans complex dynamic motions quickly and accurately at test time. Building upon our lab's sim2real efforts, the key idea is to create many complex scenes in simulation and then distill classical motion planner trajectories into a single reactive neural network policy. More details in the thread below! 👇 Open-sourced:

Motion planning in complex tasks is hard and still done via slow, explicit, traditional planners. We present a generalist Neural Motion Planner -- a single neural network that plans complex dynamic motions quickly and accurately at test time. Building upon our lab's sim2real efforts, the key idea is to create many complex scenes in simulation and then distill classical motion planner trajectories into a single reactive neural network policy. More details in the thread below! 👇 Open-sourced:

Deepak Pathak

28,642 görüntüleme • 2 yıl önce