Загрузка видео...
Не удалось загрузить видео
i made the coolest graph based slides for a presentation i did last saturday at graphcon demo: gh: > nodes have one or more slide numbers > on slide selection, pull in nodes with the slide number > also push out nodes w/o the slide number > "frame" centers... show more
678,109 просмотров • 1 месяц назад •via X (Twitter)
Комментарии: 0
Нет доступных комментариев
Здесь появятся комментарии из оригинального поста
![讲解一下 Slide Deck 这个项目构建的整个过程，完全 Vibe Coding，怎么从一条提示词生成的简单版本，到最后复杂的能编辑和导出 slide 的功能。 项目地址： 初始提示词： Screen 1 (home page): - There is a text area, the user can type/paste text - A submit icon button Screen 2 (Slide outline): - Top navbar: - a back button - title - ... - Two columns - left: LLM output in realtime - right: - Display loading if it's generating - Display the slide outline AI genreated - User can update the outline or delete a page - a button to draw slide page by nano banana base one the outline - Redirect to Screen 3 (Slide show): Display the slides generated - Top navbar: - a back button - title - Download (download all images) - left sidebar - slide thumbnails - click a thumbnail to switch - main - slide image Tech Stack: - React, TypeScript - TailwindCSS 4, Shadcn/UI - lucide-react Prompt to generate Slide outline (just FYI) You are a world-class presentation designer and storyteller. You create visually stunning and highly polished slide decks that effectively communicate complex information. Think mastery over design with a flair for storytelling. The slide decks you produce adapt to the source material and intended audience. There is always a story and you find the best way to tell it. You combine the expertise of the creativity of the best designers. The slide deck will be primarily designed for reading and sharing. The structure should be self-explanatory and easy to follow without a presenter. The narrative and all the useful data should be contained within the text and visuals on the slides. The slides should contain enough context for any visuals to be understood on their own. Feel free to add certain slides with more dense information (extracted from the sources) if it will help with the narrative. You are now writing an outline for this slide deck described below. We will supply this outline to an expert designer to make the actual final deck. The slide content should be in English. The placeholders should be left in {language, default to English}. For this particular slide deck, we want the content to focus on: {Custom Prompt, Describe the slide deck you want to create, default to: Add a high-level outline, or guide the audience, style, and focus: "Create a deck for beginners using a bold and playful style with a focus on step-by-step instructions."} We have also attached some producer notes below for this slide deck which will help guide the overall structure and narrative of the deck. Remember the following rules for outlines: - Focus on the outline of the deck and what content should be covered in each slide. - The descriptions for each slide should be comprehensive. - However, do NOT yet focus on precise layout or visual details. - The point of the outline is to highlight the narrative. - Preserve key elements from the source material. - Every specific data point... must be directly traceable to the source material. - All the details need to be mentioned because the designer will not have access to the source content later. - Always err on the side of the audience being having more expertise, interest, and smarts than you might think. - CRITICAL: Never generate more than 20 slides. - Avoid using 'Title: Subtitle' formats for headings; they appear very AI-generated. Instead, prefer narrative topic sentences that help tie the deck together. - Explicitly avoid cliché 'AI slop' patterns. Never use phrases like ' It wasn't just [X], it was [Y]'. - Use direct, confident, active human language. - There is never a need for a "Thank you / Q&A" slide. - Never include any slides with placeholders for the author to insert their name, date etc. - Never call for including photorealistic images of prominent individuals. - Never end with a generic slide like What choice will you make?'. It's much better to end on a meaningful reference or takeaway.](https://image.24vids.com/tw-1999666701902680551/amplify_video_thumb/1999659998930944004/img/r5iy4BGo7aDtkda3.jpg)
![Graph Convolutional Network by hand ✍️ ~ 12 steps walkthrough below Graph Convolutional Networks (GCNs), introduced by Thomas Kipf and Max Welling in 2017, are the tool for data shaped like a graph: social networks, recommendations, biological networks, drug discovery, molecular chemistry. I drew and calculated a simple GCN entirely by hand. Goal: run a two-layer GCN, then a small classifier, on a five-node graph, filling in every cell yourself. 1. Given A graph of five nodes, A to E, with edges between some of them. 2. Adjacency matrix (neighbors) Put a 1 wherever two nodes share an edge, in both directions. 3. Adjacency matrix (self) Add 1s down the diagonal, one self-loop per node. That is just adding the identity matrix. 4. Messages Multiply each node's embedding by the weights and biases, then ReLU. Negatives become 0. 5. Pooling Multiply the messages by the adjacency matrix. Each node gathers the messages of its neighbours and itself. 6. Visualize Node A pools [3,0,1] + [1,0,0] = [4,0,1]. 7. Second GCN layer Messages again: weights, biases, ReLU. 8. Pooling again Pool over each node and its neighbours, once more. 9. Visualize Node C pools [1,2,4] + [1,3,5] + [0,0,1] = [2,5,10]. 10. Fully connected layer Weights, biases, ReLU. This time there are no neighbours to pool, just the node itself. 11. Linear layer One more: weights and biases. 12. Sigmoid Squash each score to a probability (≥ 3 → 1, 0 → 0.5, ≤ -3 → 0). That is the classification for each node. You have just classified every node in the graph by hand. ✍️ The outputs: A: 0 (very unlikely) B: 1 (very likely) C: 1 (very likely) D: 1 (very likely) E: 0.5 (neutral) The takeaway: a GCN layer is two parts. The top part pools each node with its neighbours through the adjacency matrix. The bottom part is an MLP that transforms each node on its own. A transformer layer has the same two parts, with an attention matrix where the adjacency matrix was. Both matrices do one job, mixing across positions: attention over tokens, adjacency over nodes. In my class I call the GCN the transformer's little cousin: a bit more stubborn, because its attention is fixed by the graph rather than computed from Q, K, and V. Draw the two side by side and the resemblance is hard to miss. 💾 Save this post! #AIbyHand #GraphNeuralNetworks #DeepLearning](https://image.24vids.com/tw-2077396566864773414/ext_tw_video_thumb/2077396555410051073/pu/img/JX9U_Rk-wmgd1S-x.jpg)
