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.

this is how machine learning actually works (gradient descent with bad starting parameters)

LaurieWired

138,849 subscribers

38,694 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von luffy

luffyvor 1 Jahr

sgd be like

Profilbild von Rainmaker

Rainmakervor 2 Jahren

Can Machine Learning beat the market? Check out this post on my free Substack where I share code and commentary for an XGBoost model and a Random Forest model that both deliver powerful performances.

Profilbild von Kandrej Arpathy

Kandrej Arpathyvor 1 Jahr

that’s an oversimplification that is borderline fake news. you can make much memes that are both educational and funny

Profilbild von Salomon Metre

Salomon Metrevor 1 Jahr

😅😅

Profilbild von roro

rorovor 1 Jahr

GAN training

Profilbild von Nic B

Nic Bvor 1 Jahr

🤣

Profilbild von Jebin Einstein

Jebin Einsteinvor 1 Jahr

Just now learning “kaiming” and my timeline showing me post related to it 🤯🤯🤯🤯

Profilbild von Michael

Michaelvor 1 Jahr

Very accurate😀

Profilbild von Pehdrew

Pehdrewvor 1 Jahr

0:25 don't elaborate! 😎

Profilbild von Yacine Mahdid

Yacine Mahdidvor 1 Jahr

Reinforcement learning in the 40th step

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

141,964 Aufrufe • vor 7 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

33,044 Aufrufe • vor 9 Monaten

This is how a vending machine works

This is how a vending machine works

Historic Vids

1,048,658 Aufrufe • vor 2 Jahren

This is how the Israeli propaganda machine works.

This is how the Israeli propaganda machine works.

Quds News Network

305,822 Aufrufe • vor 2 Jahren

For small step sizes, mirror descent is equivalent to a gradient descent on a Hessian manifold.

For small step sizes, mirror descent is equivalent to a gradient descent on a Hessian manifold.

Gabriel Peyré

61,861 Aufrufe • vor 2 Jahren

This is how Bitcoin actually works…

This is how Bitcoin actually works…

Vivek Sen

44,297 Aufrufe • vor 4 Monaten

This is how a Fish counting machine works. 🐠

This is how a Fish counting machine works. 🐠

HOW THINGS WORK

6,089,650 Aufrufe • vor 2 Jahren

this viz for gradient descent with momentum is still one of my favourite examples of using an interactive component to explain an idea

this viz for gradient descent with momentum is still one of my favourite examples of using an interactive component to explain an idea

ab

17,157 Aufrufe • vor 1 Jahr

This is How This Self-Supporting Structure Actually Works

This is How This Self-Supporting Structure Actually Works

Arcfunmi

338,174 Aufrufe • vor 5 Monaten

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

117,570 Aufrufe • vor 1 Jahr

This is how gravity actually works [🎞️ thebrainmaze]

This is how gravity actually works [🎞️ thebrainmaze]

Massimo

32,911 Aufrufe • vor 23 Tagen

This is how the Wall Street actually works

This is how the Wall Street actually works

Business Hustlez

413,618 Aufrufe • vor 1 Jahr

This is how the Customer Psychology Actually Works...

This is how the Customer Psychology Actually Works...

Empire Mindset | Wealth Architect

257,171 Aufrufe • vor 9 Monaten

This is how the Wall Street actually works

This is how the Wall Street actually works

FearBuck

235,564 Aufrufe • vor 1 Jahr

This is how the Customer Psychology Actually Works...

This is how the Customer Psychology Actually Works...

Empire Mindset | Wealth Architect

20,703 Aufrufe • vor 2 Monaten

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

108,861 Aufrufe • vor 1 Jahr

Crossing Trump comes with a cost some Republicans are learning the hard way. Matt Whitlock tells @FOXNews’ Bill Melugin how Trump's political machine works, and how the GOP should wield it against Democrats this fall.

Crossing Trump comes with a cost some Republicans are learning the hard way. Matt Whitlock tells @FOXNews’ Bill Melugin how Trump's political machine works, and how the GOP should wield it against Democrats this fall.

FOX News Radio

11,664 Aufrufe • vor 19 Tagen

Ella is learning how a landline phone works

Ella is learning how a landline phone works

Barstool Spring Break

99,196 Aufrufe • vor 1 Monat

In 1998, Japanese Mathematician, Engineer and Machine Learning pioneer Shun-ichi Amari published "Natural Gradient Works Efficiently in Learning (722 Cites in Papers and 9 Cites in Patents)" and made a point that still feels fresh even today If your loss is L(θ), then the usual update θ̇ = −∇ L(θ) quietly assumes your parameter space is flat. Amari asked what happens when the model itself has geometry, described by G(θ), the Fisher information. Then the more natural direction becomes θ̇ = −G(θ)⁻¹∇ L(θ). This is the same loss, but with a different notion of distance. As the animation shows, ordinary Gradient Descent follows the raw slope and gets dragged around by distortion, while the natural gradient moves in a way that respects the geometry of the statistical model itself.

In 1998, Japanese Mathematician, Engineer and Machine Learning pioneer Shun-ichi Amari published "Natural Gradient Works Efficiently in Learning (722 Cites in Papers and 9 Cites in Patents)" and made a point that still feels fresh even today If your loss is L(θ), then the usual update θ̇ = −∇ L(θ) quietly assumes your parameter space is flat. Amari asked what happens when the model itself has geometry, described by G(θ), the Fisher information. Then the more natural direction becomes θ̇ = −G(θ)⁻¹∇ L(θ). This is the same loss, but with a different notion of distance. As the animation shows, ordinary Gradient Descent follows the raw slope and gets dragged around by distortion, while the natural gradient moves in a way that respects the geometry of the statistical model itself.

Mathelirium

45,688 Aufrufe • vor 2 Monaten