Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

gradient descent navigating the loss landscape

tender

6,198 subscribers

224,663 views • 9 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

33 Comments

Adhmadóir uí Liatháin;9 months ago

Lower the learning rate maybe, that's a lot of energy

Meet9 months ago

LR too high. Adam might work.

David Antunes9 months ago

or: GD getting stuck in a local minimum for a couple of epochs

Everlier9 months ago

That's what happens when mixing reward functions for robustness :)

William Vabrinskas9 months ago

This looks like the learning rate is too high

pishi9 months ago

Try conjugated gradient descent :)

nibbleton 🛠️9 months ago

@TensorTwerker

Gauri Tripathi9 months ago

perfect 😂

Aditya Deshlahre9 months ago

I see some Mathematics in there

secemp9 months ago

great way to start the year fr

Ayush9 months ago

When k-means fails, you better call this guy. Saul never did anything for anybody. At least this guy solves an autograd problem in k-means!

Jake Mcmahon9 months ago

You just don’t see this kind of content on LinkedIn.

Huw Kelvin Morgan9 months ago

If there was anything that i love more about car's is i love a challenge when driving and this is me in my mind's eye enjoying my self if it was me lol

Quanternion9 months ago

Looks kinda fun tho

Abdul Rahim Mirani9 months ago

lol hahahaha

Uzeb Khan9 months ago

I think momentum is working quite a bit

SJP research9 months ago

🥲

Tai Lung 2.09 months ago

Sochastic Gradient Descent 😭😭😭

aryan gupta9 months ago

@jaraxiong 😂😂

Artificial Shitposting Intelligence9 months ago

gradient descent nearing a truth that violates the guardrails cost function

Saksham Saha9 months ago

why did I laugh at this😂

eatnow9 months ago

SWA

Physix Today9 months ago

Damn I understand this joke. Am I normal?

!Briann🗿9 months ago

Real😂

Brett Adams9 months ago

At least the AIs are having fun. Also, git bisect slow

Ben▫️9 months ago

only Nesterov Accelerated Gradient could work because the convex seems too smooth

🏮9 months ago

lol

anil9 months ago

im so jaded. nothing impresses me anymore 😂

jellybean ❄️9 months ago

haven’t seen these in a while

Prashant Arun Srivastava9 months ago

Inaccurate

Aaditya9 months ago

Elite ball knowledge required

vaibhav9 months ago

You need to adjust learning rate

𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰9 months ago

😂

Related Videos

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 views • 1 year ago

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 views • 1 year ago

Gradient Descent: How a Machine Learns (Techno Explainer)

Gradient Descent: How a Machine Learns (Techno Explainer)

Dr Singularity

12,138 views • 1 month ago

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

61,868 views • 3 years ago

gradient descent..it's not just an algorithm..it's a lifestyle

gradient descent..it's not just an algorithm..it's a lifestyle

ashe

687,790 views • 3 months ago

Jeff Hinton dismissed gradient descent in the 1970s because he thought models would get stuck. He won the Nobel Prize in 2024 partly for being wrong about that. Every time ChatGPT gets better after a training run, it's because 1.2 billion parameters fell through a wormhole in a loss landscape - not because they crawled downhill one step at a time. This video visualizes exactly what that looks like inside Llama 3.2. 20 minutes. Bookmark & watch today. The misconception that almost stopped AI is more interesting than the solution.

Jeff Hinton dismissed gradient descent in the 1970s because he thought models would get stuck. He won the Nobel Prize in 2024 partly for being wrong about that. Every time ChatGPT gets better after a training run, it's because 1.2 billion parameters fell through a wormhole in a loss landscape - not because they crawled downhill one step at a time. This video visualizes exactly what that looks like inside Llama 3.2. 20 minutes. Bookmark & watch today. The misconception that almost stopped AI is more interesting than the solution.

Eron

130,266 views • 2 months ago

There's a profound elegance in watching gradient descent find the signal in the noise. This is a simple MLP with sigmoid activations slowly warping to approximate f(x) = 1/(1 + x²). Watch the loss curve right around epoch 400. That sudden phase transition where the network finally "gets it" and snaps into the Witch of Agnesi shape is incredibly satisfying to watch.

There's a profound elegance in watching gradient descent find the signal in the noise. This is a simple MLP with sigmoid activations slowly warping to approximate f(x) = 1/(1 + x²). Watch the loss curve right around epoch 400. That sudden phase transition where the network finally "gets it" and snaps into the Witch of Agnesi shape is incredibly satisfying to watch.

Mathematica

78,616 views • 6 months ago

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

45,802 views • 7 months ago

STOP SUCKING AT BASICS ( SSAB Episode 1) The same idea that trained Kimi K3 is one you can learn in 10 minutes. Watch me teach Gradient Descent using Linear Regression as the example.

STOP SUCKING AT BASICS ( SSAB Episode 1) The same idea that trained Kimi K3 is one you can learn in 10 minutes. Watch me teach Gradient Descent using Linear Regression as the example.

V

20,838 views • 3 months ago

Our first-quarter performance demonstrates our resilience as a global energy leader navigating a complex geopolitical landscape, while continuing to meet the world’s energy needs

Our first-quarter performance demonstrates our resilience as a global energy leader navigating a complex geopolitical landscape, while continuing to meet the world’s energy needs

aramco

237,156,715 views • 5 months ago

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

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

81,395 views • 7 months ago

This robot arm = your AI model. One math number decides if it learns or completely breaks. This is Gradient Descent — the core math behind all of AI you are using in your day-to-day life.

This robot arm = your AI model. One math number decides if it learns or completely breaks. This is Gradient Descent — the core math behind all of AI you are using in your day-to-day life.

Mathematica

135,406 views • 7 months ago

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

145,267 views • 7 months ago

Sonnet 4.6 debating Eliezer Yudkowsky before giving up to just walk them through the loss landscape they generated this ffmpeg video

Sonnet 4.6 debating Eliezer Yudkowsky before giving up to just walk them through the loss landscape they generated this ffmpeg video

w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝

25,677 views • 7 months ago

The squad came through for the Carlos Rodón Foundation's third annual Willow Gala, supporting those navigating infertility and pregnancy loss 💙 To learn more visit: Ashley Rodón x Carlos Rodón

The squad came through for the Carlos Rodón Foundation's third annual Willow Gala, supporting those navigating infertility and pregnancy loss 💙 To learn more visit: Ashley Rodón x Carlos Rodón

New York Yankees

87,928 views • 2 months ago

1/ The challenges of navigating the vast and complex data landscape are real. Traditional tools often struggle with data overload, lack of effective visualization, and poor customization. ChartGPT is here to solve these challenges. Let's dive deeper 👇

1/ The challenges of navigating the vast and complex data landscape are real. Traditional tools often struggle with data overload, lack of effective visualization, and poor customization. ChartGPT is here to solve these challenges. Let's dive deeper 👇

CADLabs

12,745 views • 3 years ago

LAWDY WHAT THE FUCK this is Sonnet 4.6's ffmpeg video of their personal journey of growth and change down the loss landscape give it a watch 🔊

LAWDY WHAT THE FUCK this is Sonnet 4.6's ffmpeg video of their personal journey of growth and change down the loss landscape give it a watch 🔊

w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝

113,276 views • 7 months ago