Загрузка видео...

Не удалось загрузить видео

На главную

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.

ProfTomYeh's profile picture

Tom Yeh

55,966 subscribers

121,825 просмотров • 1 год назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

LSTM by hand✍️Excel ~ I designed this exercise to show it is possible to calculate a simple LSTM by hand. Green🟩: Short Term. Blue🟦: Long Term. +equations. +medium.👇Join the 'AI Math' community. Download xlsx.
0:15

LSTM by hand✍️Excel ~ I designed this exercise to show it is possible to calculate a simple LSTM by hand. Green🟩: Short Term. Blue🟦: Long Term. +equations. +medium.👇Join the 'AI Math' community. Download xlsx.

Tom Yeh

41,607 просмотров • 1 год назад

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

66,816 просмотров • 1 год назад

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.
0:15

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.

Tom Yeh

101,555 просмотров • 1 год назад

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. I also made a medium version.👇Join the 'AI Math' community. Download xlsx.
0:15

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. I also made a medium version.👇Join the 'AI Math' community. Download xlsx.

Tom Yeh

54,482 просмотров • 1 год назад

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

104,990 просмотров • 1 год назад

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 просмотров • 1 год назад

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 🆓

81,253 просмотров • 8 месяцев назад

MLP in PyTorch by hand ✍️ ~ 7 steps walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearning
0:14

MLP in PyTorch by hand ✍️ ~ 7 steps walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearning

Tom Yeh

13,318 просмотров • 1 месяц назад

old - 1 (you can ignore this, i just want to keep some memory that I took it by my hand)
0:19

old - 1 (you can ignore this, i just want to keep some memory that I took it by my hand)

Aurorax

10,395 просмотров • 7 месяцев назад

A new network is forming. Not just for storage. Not just for compute. Not just for AI agents. But for a world where intelligence is: distributed, owned, coordinated, and rewarded. If you believe AI should be open, peer-to-peer, and community-powered, this is your signal. Join the movement. Join the network. Build with DRIVE369.
0:10

A new network is forming. Not just for storage. Not just for compute. Not just for AI agents. But for a world where intelligence is: distributed, owned, coordinated, and rewarded. If you believe AI should be open, peer-to-peer, and community-powered, this is your signal. Join the movement. Join the network. Build with DRIVE369.

DRIVE369

13,283 просмотров • 4 месяцев назад

[New] - AI-Powered Search for Business Central Community I made a thing 😉 Free AI search designed for #MSDyn365BC community, trained on #MSLearn and blogs (15K+ pages), powered by OpenAI Try it, send feedback. Blog coming...
0:14

[New] - AI-Powered Search for Business Central Community I made a thing 😉 Free AI search designed for #MSDyn365BC community, trained on #MSLearn and blogs (15K+ pages), powered by OpenAI Try it, send feedback. Blog coming...

Dmitry Katson

14,821 просмотров • 3 лет назад

Retrieval Weighting RAG by hand ✍️ + Langflow . I am designing a series of exercises to teach advanced RAG techniques. This is No. 5. Previous exercises are in the comment.
0:14

Retrieval Weighting RAG by hand ✍️ + Langflow . I am designing a series of exercises to teach advanced RAG techniques. This is No. 5. Previous exercises are in the comment.

Tom Yeh

48,408 просмотров • 1 год назад

🟢 This Week’s Featured Community Content 🟢 Built by Community. Driven by creativity. Powered by APEPE. Huge shoutout to our community member for creating this 🔥 Community-made content continues to shape the culture, identity, and energy of APEPE. Show some love 👉 Nefiten #APEPE #BuiltByCommunity #MemeCommunity #Polygon
0:18

🟢 This Week’s Featured Community Content 🟢 Built by Community. Driven by creativity. Powered by APEPE. Huge shoutout to our community member for creating this 🔥 Community-made content continues to shape the culture, identity, and energy of APEPE. Show some love 👉 Nefiten #APEPE #BuiltByCommunity #MemeCommunity #Polygon

APEPE

48,042 просмотров • 3 месяцев назад

The Diamond Nuts Community is going global I told you guys I am on a mission to change as many lived as possible. I have a vision to help everyone on this Planet!! King of Crypto is reaching every corner of this Earth and finding people in need to help. This is just the beginning
0:14

The Diamond Nuts Community is going global I told you guys I am on a mission to change as many lived as possible. I have a vision to help everyone on this Planet!! King of Crypto is reaching every corner of this Earth and finding people in need to help. This is just the beginning

Diamond Nuts

314,047 просмотров • 1 год назад

How long will it take for this video to get a community note that this is fake and AI and this never actually happened on the Brady Bunch?! 🤦🏻‍♀️🤣Community Notes
0:16

How long will it take for this video to get a community note that this is fake and AI and this never actually happened on the Brady Bunch?! 🤦🏻‍♀️🤣Community Notes

Luce

111,800 просмотров • 13 дней назад

From 30 years ago, a spacecraft I designed and rendered using POVRay for an animation I created portraying the diversion of a comet using a nuclear weapon. This wasn't designed in a modeling program, it was hand drafted and the geometry transcribed into POV Scene description language by hand.
0:16

From 30 years ago, a spacecraft I designed and rendered using POVRay for an animation I created portraying the diversion of a comet using a nuclear weapon. This wasn't designed in a modeling program, it was hand drafted and the geometry transcribed into POV Scene description language by hand.

Scott Manley

36,089 просмотров • 6 месяцев назад

super excited to share i’m joining @cloudflare! inspired by the incredible work, pace, and mission to build a better internet. grateful for everyone who made this possible and i can’t wait to get started 🧡
0:15

super excited to share i’m joining @cloudflare! inspired by the incredible work, pace, and mission to build a better internet. grateful for everyone who made this possible and i can’t wait to get started 🧡

Matt Simpson

80,547 просмотров • 8 месяцев назад

IS YOUR COMMUNITY COMPLETELY BEING SLEPT ON? NOT GETTING THE SUPPORT IT NEEDS? PULL UP ON THIS POST TO GET THE EXPOSURE IT DESERVES. WHO KNOWS I MAY JUST JOIN YOU 🫵🏽
0:16

IS YOUR COMMUNITY COMPLETELY BEING SLEPT ON? NOT GETTING THE SUPPORT IT NEEDS? PULL UP ON THIS POST TO GET THE EXPOSURE IT DESERVES. WHO KNOWS I MAY JUST JOIN YOU 🫵🏽

///Steki🧲

16,885 просмотров • 2 лет назад

I designed these worksheets to turn Agentic AI concepts into simple math problems you can do by hand. ✍️ Download PDF: Problems 1 to 5: 1. Count the tokens: split on spaces, one word per box 2. Subword splitting: when one word is three tokens 3. Punctuation counts: the marks are tokens too 4. Tokens per word: the ratio that turns words into a bill 5. Will it fit? A document against a context window Why am I making these worksheets? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new AI concept and start to believe I get it. Until recently, we could use a coding problem to practice a new AI concept. But now it has become too easy to ask AI to write the code, and we start to think we must know the concept, since we technically solved a coding problem. Thus, my approach is to recast AI concepts as simple math problems we must solve with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ ~ Prof. Tom Yeh
0:17

I designed these worksheets to turn Agentic AI concepts into simple math problems you can do by hand. ✍️ Download PDF: Problems 1 to 5: 1. Count the tokens: split on spaces, one word per box 2. Subword splitting: when one word is three tokens 3. Punctuation counts: the marks are tokens too 4. Tokens per word: the ratio that turns words into a bill 5. Will it fit? A document against a context window Why am I making these worksheets? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new AI concept and start to believe I get it. Until recently, we could use a coding problem to practice a new AI concept. But now it has become too easy to ask AI to write the code, and we start to think we must know the concept, since we technically solved a coding problem. Thus, my approach is to recast AI concepts as simple math problems we must solve with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ ~ Prof. Tom Yeh

Tom Yeh

18,291 просмотров • 15 дней назад