Loading video...

Video Failed to Load

Go Home

Autoencoder by hand✍️Excel~ I designed this exercise to show how an Encoder-Decoder network convert input to code and reconstruct input from code. It is annotated with equations, PyTorch, and graphs. 👇Join the 'AI Math' community. Download xlsx.

ProfTomYeh's profile picture

Tom Yeh

56,036 subscribers

101,555 views • 1 year ago •via X (Twitter)

ArtsScience & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Transformer by hand✍️ Excel ~ I designed this exercise to show the core math of a Transformer model is to combine columns (attention), combine rows (feed forward), and repeat.👇Join the 'AI Math' community. 👇Download xlsx.
0:17

Transformer by hand✍️ Excel ~ I designed this exercise to show the core math of a Transformer model is to combine columns (attention), combine rows (feed forward), and repeat.👇Join the 'AI Math' community. 👇Download xlsx.

Tom Yeh

66,770 views • 1 year ago

ResNet by hand✍️Excel~ I designed this exercise to compare a ResNet to an MLP and show skip-connections are simply identity matrices next to weights and biases. I also made a medium version to show how it scales. 👇Join the 'AI Math' community. Download xlsx.
0:15

ResNet by hand✍️Excel~ I designed this exercise to compare a ResNet to an MLP and show skip-connections are simply identity matrices next to weights and biases. I also made a medium version to show how it scales. 👇Join the 'AI Math' community. Download xlsx.

Tom Yeh

29,925 views • 1 year ago

AlphaFold by hand✍️ Excel ~ I designed this exercise to show (1) MSA multi-head attention, (2) Pair triangular update, two key components of the EvoFormer architecture.👇Join the AI Math community. Download xlsx.
0:18

AlphaFold by hand✍️ Excel ~ I designed this exercise to show (1) MSA multi-head attention, (2) Pair triangular update, two key components of the EvoFormer architecture.👇Join the AI Math community. Download xlsx.

Tom Yeh

104,965 views • 1 year ago

Backpropagation by hand✍️ ~ spreadsheet. I designed this exercise to show it is possible to calculate backpropagation for a non-trivial, three-layer network by hand. p.s. I just started this community to share useful resources on AI math. 👇 Join the community.
0:11

Backpropagation by hand✍️ ~ spreadsheet. I designed this exercise to show it is possible to calculate backpropagation for a non-trivial, three-layer network by hand. p.s. I just started this community to share useful resources on AI math. 👇 Join the community.

Tom Yeh

121,825 views • 1 year ago

Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~ I made this visualization to show you how to implement the multi-head attention math in PyTorch within 50 LoC. Multi-Head Attention is what makes the Transformer's performance outstanding. It captures and represents more diverse linguistic relationships and patterns, and attends to different learned input embedding spaces. The parallel computing design also makes the model more efficient.
0:10

Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~ I made this visualization to show you how to implement the multi-head attention math in PyTorch within 50 LoC. Multi-Head Attention is what makes the Transformer's performance outstanding. It captures and represents more diverse linguistic relationships and patterns, and attends to different learned input embedding spaces. The parallel computing design also makes the model more efficient.

Yan Chen

33,255 views • 1 year ago

understand AI like this: if your input is dumb, your output will be dumb, and if your input is creative, your output will be creative. this is it. so, you need to provide about 70% of the context from your own brain to the ai to get the best outputs.
0:15

understand AI like this: if your input is dumb, your output will be dumb, and if your input is creative, your output will be creative. this is it. so, you need to provide about 70% of the context from your own brain to the ai to get the best outputs.

ViralOps

128,487 views • 4 months ago

OTP Input by sucodee More OTP code designs:
0:13

OTP Input by sucodee More OTP code designs:

Collect UI

18,883 views • 5 days ago

Introducing Visual Copilot ✨🧵👇 Convert designs into clean, responsive code with AI: ➡️ Run the Builder Figma plugin ➡️ Convert code to your framework ➡️ Chat to refine the code ➡️ Sync the code to your site or app Learn more:
0:14

Introducing Visual Copilot ✨🧵👇 Convert designs into clean, responsive code with AI: ➡️ Run the Builder Figma plugin ➡️ Convert code to your framework ➡️ Chat to refine the code ➡️ Sync the code to your site or app Learn more:

Builder.io

68,712 views • 2 years ago

Here's what happen when you try to input any cheat code from the first Tomb Raider into the second one This was used to troll gamers who wanted the infamous nude code
0:19

Here's what happen when you try to input any cheat code from the first Tomb Raider into the second one This was used to troll gamers who wanted the infamous nude code

𝐋𝐨𝐰 𝐏𝐨𝐥𝐲 𝐃𝐞𝐩𝐫𝐞𝐬𝐬𝐢𝐨𝐧

115,608 views • 3 years ago

The new controller input UI in VTube Studio was designed by Girutea ✨ Look at how cute it is!!!!!!
0:11

The new controller input UI in VTube Studio was designed by Girutea ✨ Look at how cute it is!!!!!!

Denchi ⚒ Iron Vertex

42,448 views • 3 months ago

By now, you've probably heard about Gemini Omni, our new model designed to create anything from any input, starting with video. But... what's the big deal? Let’s break it down 🧵👇
0:10

By now, you've probably heard about Gemini Omni, our new model designed to create anything from any input, starting with video. But... what's the big deal? Let’s break it down 🧵👇

Google AI

225,246 views • 1 month ago

At MIT, I learned about RNNs in my NLP class with Prof. Michael Collins. He built a model from my keystrokes to predict who I was. To me, it felt like a magic box. Years later, when I had to teach RNNs, I forced myself to go inside the box. ⬇️ Download: First, with a tiny example on paper by hand ✍️. Then, a slightly larger one in Excel. That’s when it finally clicked: 👉 The weights are reused (weight matrices on the left side) 👉 The hidden states are passed down (H's) When I built it by hand and saw everything visually, it clicked, just math you can actually trace. Now I try to give others the same “aha!” moment I had. ⬇️ Download Excel:
0:19

At MIT, I learned about RNNs in my NLP class with Prof. Michael Collins. He built a model from my keystrokes to predict who I was. To me, it felt like a magic box. Years later, when I had to teach RNNs, I forced myself to go inside the box. ⬇️ Download: First, with a tiny example on paper by hand ✍️. Then, a slightly larger one in Excel. That’s when it finally clicked: 👉 The weights are reused (weight matrices on the left side) 👉 The hidden states are passed down (H's) When I built it by hand and saw everything visually, it clicked, just math you can actually trace. Now I try to give others the same “aha!” moment I had. ⬇️ Download Excel:

Tom Yeh

220,671 views • 8 months ago

🧵 Go from nature to code with Gemini 2.5 Pro 🍃 Each of these were created with the same prompt: Transform this image into a code-based representation of its natural behavior. Original input image on the left. Gemini output on the right.
0:08

🧵 Go from nature to code with Gemini 2.5 Pro 🍃 Each of these were created with the same prompt: Transform this image into a code-based representation of its natural behavior. Original input image on the left. Gemini output on the right.

Google

134,425 views • 1 year ago

FC is designed to reflect the network’s long-term development. Its value is shaped by how many people actually use the network and how much they rely on it. In other words, the growth of the community goes hand in hand with the value of FC. → As the community grows, activity increases. As activity increases, FC becomes more significant.
0:10

FC is designed to reflect the network’s long-term development. Its value is shaped by how many people actually use the network and how much they rely on it. In other words, the growth of the community goes hand in hand with the value of FC. → As the community grows, activity increases. As activity increases, FC becomes more significant.

Unich.com 🆓

81,081 views • 6 months ago

When Ghostty detects a password input prompt, it now changes the cursor to a lock and on macOS enables the secure input API. When the secure input API is enabled, we show a neat, animated icon that explains what's going on when clicked. Another example of native UI wins (imo). Secure Input is the macOS system API that prevents accessibility APIs from reading your keystrokes, so things like screen recording software and so on can't read your passwords. Other terminals on macOS support secure input. I think only iTerm also supports secure input on password detection. So as a disclaimer, I'm not trying to claim this as a huge innovation, I just think our implementation is nice. 😊
0:13

When Ghostty detects a password input prompt, it now changes the cursor to a lock and on macOS enables the secure input API. When the secure input API is enabled, we show a neat, animated icon that explains what's going on when clicked. Another example of native UI wins (imo). Secure Input is the macOS system API that prevents accessibility APIs from reading your keystrokes, so things like screen recording software and so on can't read your passwords. Other terminals on macOS support secure input. I think only iTerm also supports secure input on password detection. So as a disclaimer, I'm not trying to claim this as a huge innovation, I just think our implementation is nice. 😊

Mitchell Hashimoto

81,646 views • 1 year ago

when our precious things are born from code, they may take our input
0:11

when our precious things are born from code, they may take our input

m_11

27,367 views • 6 months ago

I'M RUNNING A NICE SALE FOR MY COMMISSIONS THIS CHRISTMAS! Input my code "DOPPCHRISTMAS" to get 15% off and get a free chibi as well!
0:14

I'M RUNNING A NICE SALE FOR MY COMMISSIONS THIS CHRISTMAS! Input my code "DOPPCHRISTMAS" to get 15% off and get a free chibi as well!

🐬 Doppy | !!!C0MM1SSIONS OPEN!!!

11,618 views • 6 months ago

This animation is what kickstarted Code Blue's development, and I wanted to use a version of this as an intro to Code Blue, but I ultimately decided against it as Code Blue was already late, and requiring a partial re-render, and I didn't think this scene would hit quite the same
0:10

Sensitive content

This animation is what kickstarted Code Blue's development, and I wanted to use a version of this as an intro to Code Blue, but I ultimately decided against it as Code Blue was already late, and requiring a partial re-render, and I didn't think this scene would hit quite the same

Qualtro 🔞

129,861 views • 3 years ago

✍️ I wrote an article on programming blur shaders for beginners. You do not need to be adept at either math or programming to understand how it works :) Going from the most basic/straightforward type of blur, to what you see below, and more! Lots of pretty pictures, media, and interactive code to learn from. -- Box blur, with clipping and radial weighting. (So, no longer really a box blur...?) 🔍 #gamedev #indiedev #unity3d
0:15

✍️ I wrote an article on programming blur shaders for beginners. You do not need to be adept at either math or programming to understand how it works :) Going from the most basic/straightforward type of blur, to what you see below, and more! Lots of pretty pictures, media, and interactive code to learn from. -- Box blur, with clipping and radial weighting. (So, no longer really a box blur...?) 🔍 #gamedev #indiedev #unity3d

Mirza Beig

120,676 views • 4 months ago