[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74163":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":8,"languages":8,"totalLinesOfCode":8,"stars":9,"forks":10,"watchers":11,"openIssues":12,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":12,"stars7d":14,"stars30d":15,"stars90d":13,"forks30d":13,"starsTrendScore":16,"compositeScore":17,"rankGlobal":8,"rankLanguage":8,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":8,"pushedAt":8,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":13,"starSnapshotCount":13,"syncStatus":26,"lastSyncTime":27,"discoverSource":28},74163,"ai-by-hand-excel","ImagineAILab\u002Fai-by-hand-excel","ImagineAILab",null,6156,762,108,5,0,9,62,15,39.65,"MIT License",false,"main",true,[],"2026-06-12 02:03:23","# ai-by-hand-excel\n\nAI by Hand ✍️ Exercises in Excel\n\n![](gallery.png)\n\n## Basic\n* Softmax\n* LeakyReLU\n* Temperature\n\n## Advanced\n* Multi Layer Perceptron (MLP)\n* Backpropagation\n* Recurrent Neural Network (RNN)\n* Long Short Term Memory (LSTM) (+ Seq2Seq)\n* Extended Long Short Term Memory (xLSTM)\n* Residual Network (ResNet)\n* Transformer - Simple\n* Transformer - Full Stack\n* Self-Attention\n* Multihead Attention\n* Autoencoder (AE)\n* Mamba\n* AlphaFold\n\n## Lectures\n\n### 🔥 NEW: DeepSeek \nMulti-head Latent Attention + Mixture of Experts\n(blank only)\n\n[View](https:\u002F\u002Fo365coloradoedu-my.sharepoint.com\u002F:x:\u002Fg\u002Fpersonal\u002Fpeye9704_colorado_edu\u002FEfAlZg6tnotMtEb3N0TA_98BWFdAiqD24mc-MqETTDoVUQ?e=dh4Ncq)\n| [Download](lectures\u002FDeepSeek-blank.xlsx)\n![deepseek](assets\u002Fdeepseek.png)\n\n## Workbook\n1. Dot Product\n2. Matrix Multiplication\n3. Linear Layer\n\n## Coming Soon\n* Generative Adversarial Network (GAN)\n* Variational Autoencoder (VAE)\n* U-Net\n* CLIP\n* more ...\n","ai-by-hand-excel 是一个在 Excel 中手动实现各种人工智能算法的教育项目。它通过基础和高级两部分展示了从简单的激活函数如 Softmax 和 LeakyReLU 到复杂的神经网络结构例如 LSTM、Transformer 以及 ResNet 等多种模型的手动构建过程，特别强调了对反向传播等关键概念的理解。此外，该项目还提供了关于最新技术如 DeepSeek 的讲座材料。此项目非常适合希望深入理解机器学习背后数学原理的学生或开发者使用，在没有复杂编程环境的情况下也能进行有效的学习与实践。",2,"2026-06-11 03:49:06","high_star"]