Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

[Transformer] by Hand✍️📺 5-minute Video Tutorial Anna Rahn made this short video to explain the Transformer exercise for my Computer Vision course last spring. In 5 minutes, she demonstrates the key calculations of the Transformer by hand with pen and paper! Anna is a fantastic student. I am lucky...

ProfTomYeh's profile picture

Tom Yeh

55,873 subscribers

133,460 görüntüleme • 2 yıl önce •via X (Twitter)

Sağlık & İyilikEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Rob Freeman profil fotoğrafı
Rob Freeman2 yıl önce

Nice illustration of the two dimensions. Though obscuring prediction as unsupervised learning parameter. Ironically I often cite the impossibility of ordering people simultaneously by height and weight to argue why transformers fail to capture all the information in a data set.

Tom Yeh profil fotoğrafı
Tom Yeh2 yıl önce

One way is to use multi head. But it still has limits.

Tameva baman profil fotoğrafı
Tameva baman2 yıl önce

Very nice it helped me understand the transformer. Can I seek your permission to translate it in hindi and publish it please?

Tom Yeh profil fotoğrafı
Tom Yeh2 yıl önce

Yes. You have my full support.

daved profil fotoğrafı
daved2 yıl önce

This seems like a wonderful explanation of what. It feels like there's a lack of an explanation of why.

memerinski profil fotoğrafı
memerinski2 yıl önce

This app has destroyed my attention span

Sachin Kumar profil fotoğrafı
Sachin Kumar2 yıl önce

Fantastic Explanation @ProfTomYeh Sir👍

iskender profil fotoğrafı
iskender2 yıl önce

Hello, it is a very nice training video. Would you mind if I translated the video into Turkish and published it on YouTube?

Tom Yeh profil fotoğrafı
Tom Yeh2 yıl önce

Great idea! I fully support your effort.

Maxin 🇬🇭 profil fotoğrafı
Maxin 🇬🇭2 yıl önce

🔥🔥

Benzer Videolar

Anna Rahn's video demonstration of Multi-Layer Perceptron (MLP) by hand ✍️ Anna made this short video for my computer vision course in the spring semester. Together with the spreadsheet exercise I posted yesterday, I hope they help more people understand deep neural networks!
3:35

Anna Rahn's video demonstration of Multi-Layer Perceptron (MLP) by hand ✍️ Anna made this short video for my computer vision course in the spring semester. Together with the spreadsheet exercise I posted yesterday, I hope they help more people understand deep neural networks!

Tom Yeh

120,405 görüntüleme • 1 yıl önce

Transformer by hand ✍️ in Excel ~ I just released my first-ever "Full-Stack" implementation of the Transformer model. 👇Download xlsx to give it a try!
1:02

Transformer by hand ✍️ in Excel ~ I just released my first-ever "Full-Stack" implementation of the Transformer model. 👇Download xlsx to give it a try!

Tom Yeh

2,997,651 görüntüleme • 1 yıl önce

Transformer by hand✍️
0:29

Transformer by hand✍️

Tom Yeh

29,650 görüntüleme • 7 ay önce

I calculated a poster-size Transformer model by hand✍️
0:29

I calculated a poster-size Transformer model by hand✍️

Tom Yeh

112,800 görüntüleme • 1 yıl önce

Transformer by hand ✍️ Given input X, this exercise goes through the key equations behind the 𝗦𝗲𝗹𝗳 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 layer and the 𝗙𝗲𝗲𝗱 𝗙𝗼𝗿𝘄𝗮𝗿𝗱 layer, showing you how X is transformed into Y.
0:29

Transformer by hand ✍️ Given input X, this exercise goes through the key equations behind the 𝗦𝗲𝗹𝗳 𝗔𝘁𝘁𝗲𝗻𝘁𝗶𝗼𝗻 layer and the 𝗙𝗲𝗲𝗱 𝗙𝗼𝗿𝘄𝗮𝗿𝗱 layer, showing you how X is transformed into Y.

Tom Yeh

15,488 görüntüleme • 1 yıl önce

llm.c by Hand✍️ C programming + matrix multiplication by hand This combination is perhaps as low as we can get to explain how the Transformer works. Special thanks to Andrej Karpathy for encouraging early feedback and tetsuo //: 👾 for helping me understand the pragma magic. I hope this exercise can help people peak further into the LLM black box.
0:44

llm.c by Hand✍️ C programming + matrix multiplication by hand This combination is perhaps as low as we can get to explain how the Transformer works. Special thanks to Andrej Karpathy for encouraging early feedback and tetsuo //: 👾 for helping me understand the pragma magic. I hope this exercise can help people peak further into the LLM black box.

Tom Yeh

302,688 görüntüleme • 2 yıl önce

Can you calculate a Vision Transformer (ViT) by hand? ✍️ If you can, come join me next week at the LLM Paper Club. I will extend ViT to Llama 1 -> 2 -> 3 -> 4 live. Event link below.
0:34

Can you calculate a Vision Transformer (ViT) by hand? ✍️ If you can, come join me next week at the LLM Paper Club. I will extend ViT to Llama 1 -> 2 -> 3 -> 4 live. Event link below.

Tom Yeh

79,441 görüntüleme • 1 yıl önce

Mamba by hand ✍️ ~ I made this exercise as I studied the math in the Mamba paper. It is a small yet complete Mamba implementation. Thanks Albert Gu for answering my questions and checking. 👇Join the 'AI Math' community. Download xlsx.
0:21

Mamba by hand ✍️ ~ I made this exercise as I studied the math in the Mamba paper. It is a small yet complete Mamba implementation. Thanks Albert Gu for answering my questions and checking. 👇Join the 'AI Math' community. Download xlsx.

Tom Yeh

55,445 görüntüleme • 1 yıl önce

A transformer got his ass beat for holding up the train for 5 minutes
0:35

A transformer got his ass beat for holding up the train for 5 minutes

LASHY BILLS

20,202 görüntüleme • 9 ay önce

Transformer Explainer Really cool interactive tool to learn about the inner workings of a Transformer model. Apparently, it runs a GPT-2 instance locally in the user's browser and allows you to experiment with your own inputs. This is a nice tool to learn more about the different components inside the Transformer and the transformations that occur. Tool:
0:29

Transformer Explainer Really cool interactive tool to learn about the inner workings of a Transformer model. Apparently, it runs a GPT-2 instance locally in the user's browser and allows you to experiment with your own inputs. This is a nice tool to learn more about the different components inside the Transformer and the transformations that occur. Tool:

elvis

121,921 görüntüleme • 1 yıl önce

Two years ago Anna made our first-ever AI by Hand ✍️ video, calculating one neuron. Next Wednesday (11/5) Anna will lead our 20th AI by Hand workshop! RSVP: To celebrate this milestone, we are following up with two international workshops: 21st Workshop in Arabic (11/12) 22nd Workshop in BR Portuguese (11/19) We are planning more global learning opportunities like these. Join the 20th AI by Hand workshop 🔗
2:46

Two years ago Anna made our first-ever AI by Hand ✍️ video, calculating one neuron. Next Wednesday (11/5) Anna will lead our 20th AI by Hand workshop! RSVP: To celebrate this milestone, we are following up with two international workshops: 21st Workshop in Arabic (11/12) 22nd Workshop in BR Portuguese (11/19) We are planning more global learning opportunities like these. Join the 20th AI by Hand workshop 🔗

Tom Yeh

11,685 görüntüleme • 8 ay önce

Evolution of Deep Learning by Hand ✍️ As my tribute to Geoff Hinton's Nobel Prize, I drew this animation to illustrate the key idea behind Hinton's major contributions to deep learning over the years, with artistic liberty. ---- 100% original, made by hand ✍️ Join 40k readers of my newsletter:
1:05

Evolution of Deep Learning by Hand ✍️ As my tribute to Geoff Hinton's Nobel Prize, I drew this animation to illustrate the key idea behind Hinton's major contributions to deep learning over the years, with artistic liberty. ---- 100% original, made by hand ✍️ Join 40k readers of my newsletter:

Tom Yeh

110,697 görüntüleme • 8 ay önce

🚨 Gonda power department used fan and water to cool down transformer. STAFF : "The temperature in the region is currently around 38 to 40 degrees Celsius. "The transformer, however, is operating at approximately 75 degrees Celsius" "So, Every 30 minutes, we spray water on the transformer to keep temperature safe"
1:09

🚨 Gonda power department used fan and water to cool down transformer. STAFF : "The temperature in the region is currently around 38 to 40 degrees Celsius. "The transformer, however, is operating at approximately 75 degrees Celsius" "So, Every 30 minutes, we spray water on the transformer to keep temperature safe"

News Algebra

159,687 görüntüleme • 1 ay önce

1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy
0:21

1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy

Christos Tzamos

1,819,671 görüntüleme • 4 ay önce

😀😀A short video to help you understand the Hybrid Mamba Transformer architecture behind the Hunyuan T1 & Turbo S models. Produced by EyeOpenAI.
5:19

😀😀A short video to help you understand the Hybrid Mamba Transformer architecture behind the Hunyuan T1 & Turbo S models. Produced by EyeOpenAI.

Tencent HY

21,922 görüntüleme • 1 yıl önce

GUYS!! NIGERIA, AEDC, AND TINUBU HAPPENED TO MY SMALL COMMUNITY IN LUGBE YESTERDAY!!!😥 For almost 3 years since I built my small hut in this community, we have been battling with epileptic power situation due to the overloaded Transformer which has been serving 3 communities including mine. In December 2025, after myself and a few community members spearheaded a regime change and ensured a proper election was conducted. After the election, we told the newly elected chairman (who happens to be my very very good friend) that the priority is for us to get our own dedicated Transformer for the community. Initially, we were thinking of buying. But considering it will cost over N20million to buy a 500KVA Transformer and another N15million plus for accessories and installation, the mission looked impossible. Then I and others told the Chairman that we can actually give it a try an reach out to the aedcelectricity for a Transformer given that the NERC Nigeria has told Nigerians that it is the responsibility of the DISCOs to provide Transformer and any power related infrastructure to any community or area in need of such infrastructure. Considering the Nigerian factor, many, infact, almost the entire community said it was never going to be possible for AEDC to give us a Transformer free of charge. But as someone who has been an advocate of government and who has always benefited from government by following due process, I encouraged my community and the Chairman that this is actually worth a try. In January 2026, we drafted a Transformer request letter and submitted to the AEDC Head Office at Wuse Zone 4, and the processes began. Low and behold, in less than 4 months, the AEDC, yesterday, delivered a brand new 500KVA Transformer with complete accessories to my community FREE-OF-CHARGE!🤸‍♂️🕺 I have told my community people that we have started benefitting our own share of the N3.3trillion approved by President Bola Ahmed Tinubu to GENCOs and all of us have agreed that come 2027, it is TINUBU OR NOTHING!!!🤗💪🏾 God bless the AEDC! God bless NERC!! God bless President Tinubu!!! God bless Nigeria 🇳🇬🙏🏾
0:08

GUYS!! NIGERIA, AEDC, AND TINUBU HAPPENED TO MY SMALL COMMUNITY IN LUGBE YESTERDAY!!!😥 For almost 3 years since I built my small hut in this community, we have been battling with epileptic power situation due to the overloaded Transformer which has been serving 3 communities including mine. In December 2025, after myself and a few community members spearheaded a regime change and ensured a proper election was conducted. After the election, we told the newly elected chairman (who happens to be my very very good friend) that the priority is for us to get our own dedicated Transformer for the community. Initially, we were thinking of buying. But considering it will cost over N20million to buy a 500KVA Transformer and another N15million plus for accessories and installation, the mission looked impossible. Then I and others told the Chairman that we can actually give it a try an reach out to the aedcelectricity for a Transformer given that the NERC Nigeria has told Nigerians that it is the responsibility of the DISCOs to provide Transformer and any power related infrastructure to any community or area in need of such infrastructure. Considering the Nigerian factor, many, infact, almost the entire community said it was never going to be possible for AEDC to give us a Transformer free of charge. But as someone who has been an advocate of government and who has always benefited from government by following due process, I encouraged my community and the Chairman that this is actually worth a try. In January 2026, we drafted a Transformer request letter and submitted to the AEDC Head Office at Wuse Zone 4, and the processes began. Low and behold, in less than 4 months, the AEDC, yesterday, delivered a brand new 500KVA Transformer with complete accessories to my community FREE-OF-CHARGE!🤸‍♂️🕺 I have told my community people that we have started benefitting our own share of the N3.3trillion approved by President Bola Ahmed Tinubu to GENCOs and all of us have agreed that come 2027, it is TINUBU OR NOTHING!!!🤗💪🏾 God bless the AEDC! God bless NERC!! God bless President Tinubu!!! God bless Nigeria 🇳🇬🙏🏾

𝒀𝑨𝑺𝑺𝑬𝑹 𝑨𝑺𝑬𝑲𝑶𝑴𝑬 𝑮𝑨𝑹𝑩𝑨, PGD, MLSCM

52,892 görüntüleme • 3 ay önce

I am finally "putting pen to paper", so to speak, on my magnum opus Video Essay, "The Untold Midwestern Origins of Speedrunning". I have a script I like, and am working through the editing process now. Enjoy this short content which is a sort of teaser, in the meantime.
0:31

I am finally "putting pen to paper", so to speak, on my magnum opus Video Essay, "The Untold Midwestern Origins of Speedrunning". I have a script I like, and am working through the editing process now. Enjoy this short content which is a sort of teaser, in the meantime.

Goose

13,449 görüntüleme • 5 ay önce

“My marriage to PM Nikol Pashinyan has ended. I am leaving the government residence,” Anna Hakobyan said in a video statement. In response, Nikol Pashinyan wrote: “I treat Anna’s decision with respect. Over the past 30 years, on all my most difficult days, she has been by my side, my support and my pillar. I am not sure whether I have been the same for her. Perhaps I have caused her more bitterness, for which I apologize.”
5:50

“My marriage to PM Nikol Pashinyan has ended. I am leaving the government residence,” Anna Hakobyan said in a video statement. In response, Nikol Pashinyan wrote: “I treat Anna’s decision with respect. Over the past 30 years, on all my most difficult days, she has been by my side, my support and my pillar. I am not sure whether I have been the same for her. Perhaps I have caused her more bitterness, for which I apologize.”

Alphanews Armenian Network

39,727 görüntüleme • 4 ay önce

Announcing How Transformer LLMs Work, created with Jay Alammar and Maarten Grootendorst, co-authors of the beautifully illustrated book, “Hands-On Large Language Models.” This course offers a deep dive into the inner workings of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI; in fact, the "GPT" in ChatGPT stands for "Generative Pre-Trained Transformer." Originally introduced in the Google Brain team's groundbreaking 2017 paper "Attention Is All You Need," by Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, Anthropic and DeepSeek. In this course, you’ll learn in detail how LLMs process text. You'll also work through code examples that illustrate that transformer's individual components. In details, you’ll learn: - How the representation of language has evolved, from Bag-of-Words to Word2Vec embeddings to the transformer architecture that captures a word's meanings taking into account the context of other words in the input. - How inputs are broken down into tokens before they are sent to the language model. - The details of a transformer's main stages: Tokenization and embedding, the stack of transformer blocks, and the language model head. - The inner workings of the transformer block, including attention, which calculates relevance scores, and the feedforward layer, which incorporates stored information learned in training. - How cached calculations make transformers faster. - Some of the most recent ideas in the latest models such as Mixture-of-Experts (MoE) which uses multiple sub-models and a router on each layer to improve the quality of LLMs. By the end of this course, you’ll have a deep understanding of how LLMs actually process text and be able to read through papers describing the latest models and understand the details. Gaining this intuition will improve your approach to building LLM applications. Please sign up here:
3:36

Announcing How Transformer LLMs Work, created with Jay Alammar and Maarten Grootendorst, co-authors of the beautifully illustrated book, “Hands-On Large Language Models.” This course offers a deep dive into the inner workings of the transformer architecture that powers large language models (LLMs). The transformer architecture revolutionized generative AI; in fact, the "GPT" in ChatGPT stands for "Generative Pre-Trained Transformer." Originally introduced in the Google Brain team's groundbreaking 2017 paper "Attention Is All You Need," by Vaswani and others, transformers were a highly scalable model for machine translation tasks. Variants of this architecture now power today’s LLMs such as those from OpenAI, Google, Meta, Cohere, Anthropic and DeepSeek. In this course, you’ll learn in detail how LLMs process text. You'll also work through code examples that illustrate that transformer's individual components. In details, you’ll learn: - How the representation of language has evolved, from Bag-of-Words to Word2Vec embeddings to the transformer architecture that captures a word's meanings taking into account the context of other words in the input. - How inputs are broken down into tokens before they are sent to the language model. - The details of a transformer's main stages: Tokenization and embedding, the stack of transformer blocks, and the language model head. - The inner workings of the transformer block, including attention, which calculates relevance scores, and the feedforward layer, which incorporates stored information learned in training. - How cached calculations make transformers faster. - Some of the most recent ideas in the latest models such as Mixture-of-Experts (MoE) which uses multiple sub-models and a router on each layer to improve the quality of LLMs. By the end of this course, you’ll have a deep understanding of how LLMs actually process text and be able to read through papers describing the latest models and understand the details. Gaining this intuition will improve your approach to building LLM applications. Please sign up here:

Andrew Ng

253,812 görüntüleme • 1 yıl önce

After decades of being a film maker and nearly 5 years of working with AI and Video I have finally decided it's time to drop a video tutorial course on my workflow and technique for you all. Details in the clip yo
0:53

After decades of being a film maker and nearly 5 years of working with AI and Video I have finally decided it's time to drop a video tutorial course on my workflow and technique for you all. Details in the clip yo

Trisha Code

41,005 görüntüleme • 8 ay önce