Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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 Aufrufe • vor 7 Monaten •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

28 Kommentare

Profilbild von Athrix ☄️

Athrix ☄️vor 7 Monaten

Noicee

Profilbild von Harsh Jain

Harsh Jainvor 7 Monaten

Crazy buddy 🥶

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

@HarshJain_Coder Thnx

Profilbild von Humi

Humivor 7 Monaten

oohh cooooll

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

Thnx

Profilbild von Zerion

Zerionvor 7 Monaten

Woo super cool bhai

Profilbild von Tħ∀TΣΔGIC∀LCΔT

Tħ∀TΣΔGIC∀LCΔTvor 7 Monaten

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!

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

@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

Profilbild von Tħ∀TΣΔGIC∀LCΔT

Tħ∀TΣΔGIC∀LCΔTvor 7 Monaten

@DuskyDaily mean squared error if I remember correctly

Profilbild von Yosefu

Yosefuvor 7 Monaten

Right what I needed to see Thank you

Profilbild von akansha

akanshavor 7 Monaten

damnn cool

Profilbild von Ruchira

Ruchiravor 7 Monaten

Lesgoooo

Profilbild von Manvi✨

Manvi✨vor 7 Monaten

Cool

Profilbild von kushzz

kushzzvor 7 Monaten

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

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

45 sec

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

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

Profilbild von Sharav Arora

Sharav Aroravor 6 Monaten

superbb

Profilbild von Armandeep Singh Bains

Armandeep Singh Bainsvor 5 Monaten

Kindly check your dm.

Profilbild von Apoorva

Apoorvavor 7 Monaten

Keep going buddy like this

Profilbild von PsychoBunny ⚒️

PsychoBunny ⚒️vor 5 Monaten

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

Profilbild von silicognition

silicognitionvor 7 Monaten

@clumsyaf222 cuda or cpu?

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

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

Profilbild von Kushagra

Kushagravor 7 Monaten

Insane brother. Now predict XOR gate

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

Yes

Profilbild von Devster

Devstervor 7 Monaten

damw it's is soo cool

Profilbild von sonu

sonuvor 7 Monaten

Which GPU you have for run 300K epochs 🫨

Profilbild von AADITYANSHA

AADITYANSHAvor 7 Monaten

i3 2nd gen Intel processor 🤣

Profilbild von sonu

sonuvor 7 Monaten

Not possible 😂

Ähnliche Videos

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 8 Monaten

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 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 7 Tagen

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 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 4 Monaten

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 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 6 Monaten

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 9 Monaten

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 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 2 Jahren