AashishAIHub/DeepLearning
0
1<!DOCTYPE html>2<html lang="en">3<head>4 <meta charset="UTF-8">5 <meta name="viewport" content="width=device-width, initial-scale=1.0">6 <title>Complete Deep Learning & Computer Vision Curriculum</title>7 <style>8 * {9 margin: 0;10 padding: 0;11 box-sizing: border-box;12 }13 14 :root {15 --bg: #0f1419;16 --surface: #1a1f2e;17 --text: #e4e6eb;18 --text-dim: #b0b7c3;19 --cyan: #00d4ff;20 --orange: #ff6b35;21 --green: #00ff88;22 --yellow: #ffa500;23 }24 25 body {26 font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;27 background: var(--bg);28 color: var(--text);29 line-height: 1.6;30 overflow-x: hidden;31 }32 33 .container {34 max-width: 1400px;35 margin: 0 auto;36 padding: 20px;37 }38 39 header {40 text-align: center;41 margin-bottom: 40px;42 padding: 30px 0;43 border-bottom: 2px solid var(--cyan);44 }45 46 h1 {47 font-size: 2.5em;48 background: linear-gradient(135deg, var(--cyan), var(--orange));49 -webkit-background-clip: text;50 -webkit-text-fill-color: transparent;51 margin-bottom: 10px;52 }53 54 .subtitle {55 color: var(--text-dim);56 font-size: 1.1em;57 }58 59 .dashboard { display: none; }60 .dashboard.active { display: block; }61 62 .grid {63 display: grid;64 grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));65 gap: 25px;66 margin: 40px 0;67 }68 69 .card {70 background: linear-gradient(135deg, rgba(0, 212, 255, 0.1), rgba(255, 107, 53, 0.1));71 border: 2px solid var(--cyan);72 border-radius: 12px;73 padding: 30px;74 cursor: pointer;75 transition: all 0.3s ease;76 text-align: center;77 }78 79 .card:hover {80 transform: translateY(-5px);81 box-shadow: 0 10px 30px rgba(0, 212, 255, 0.2);82 border-color: var(--orange);83 }84 85 .card-icon {86 font-size: 3em;87 margin-bottom: 15px;88 }89 90 .card h3 {91 color: var(--cyan);92 font-size: 1.5em;93 margin-bottom: 10px;94 }95 96 .card p {97 color: var(--text-dim);98 font-size: 0.95em;99 }100 101 .category-label {102 display: inline-block;103 margin-top: 10px;104 padding: 5px 12px;105 background: rgba(0, 212, 255, 0.2);106 border-radius: 20px;107 font-size: 0.85em;108 color: var(--green);109 }110 111 .module { display: none; }112 .module.active { display: block; animation: fadeIn 0.3s ease; }113 114 @keyframes fadeIn {115 from { opacity: 0; }116 to { opacity: 1; }117 }118 119 .btn-back {120 padding: 10px 20px;121 background: var(--orange);122 color: var(--bg);123 border: none;124 border-radius: 6px;125 cursor: pointer;126 font-weight: 600;127 margin-bottom: 25px;128 transition: all 0.3s ease;129 }130 131 .btn-back:hover { background: var(--cyan); }132 133 .tabs {134 display: flex;135 gap: 10px;136 margin-bottom: 30px;137 flex-wrap: wrap;138 justify-content: center;139 border-bottom: 1px solid rgba(0, 212, 255, 0.2);140 padding-bottom: 15px;141 overflow-x: auto;142 }143 144 .tab-btn {145 padding: 10px 20px;146 background: var(--surface);147 color: var(--text);148 border: 2px solid transparent;149 border-radius: 6px;150 cursor: pointer;151 font-size: 0.95em;152 transition: all 0.3s ease;153 font-weight: 500;154 white-space: nowrap;155 }156 157 .tab-btn:hover {158 background: rgba(0, 212, 255, 0.1);159 border-color: var(--cyan);160 }161 162 .tab-btn.active {163 background: var(--cyan);164 color: var(--bg);165 border-color: var(--cyan);166 }167 168 .tab { display: none; }169 .tab.active { display: block; animation: fadeIn 0.3s ease; }170 171 .section {172 background: var(--surface);173 border: 1px solid rgba(0, 212, 255, 0.2);174 border-radius: 10px;175 padding: 30px;176 margin-bottom: 25px;177 transition: all 0.3s ease;178 }179 180 .section:hover {181 border-color: var(--cyan);182 box-shadow: 0 0 20px rgba(0, 212, 255, 0.1);183 }184 185 h2 {186 color: var(--cyan);187 font-size: 1.8em;188 margin-bottom: 15px;189 }190 191 h3 {192 color: var(--orange);193 font-size: 1.3em;194 margin-top: 20px;195 margin-bottom: 12px;196 }197 198 h4 {199 color: var(--green);200 font-size: 1.1em;201 margin-top: 15px;202 margin-bottom: 10px;203 }204 205 p { margin-bottom: 15px; line-height: 1.8; }206 207 ul { margin-left: 20px; margin-bottom: 15px; }208 ul li { margin-bottom: 8px; }209 210 .info-box {211 background: linear-gradient(135deg, rgba(0, 212, 255, 0.1), rgba(255, 107, 53, 0.1));212 border: 1px solid var(--cyan);213 border-radius: 8px;214 padding: 20px;215 margin: 20px 0;216 }217 218 .box-title {219 color: var(--orange);220 font-weight: 700;221 margin-bottom: 10px;222 font-size: 1.1em;223 }224 225 .box-content {226 color: var(--text-dim);227 line-height: 1.7;228 }229 230 .formula {231 background: rgba(0, 212, 255, 0.1);232 border: 1px solid var(--cyan);233 border-radius: 8px;234 padding: 20px;235 margin: 20px 0;236 font-family: 'Courier New', monospace;237 overflow-x: auto;238 line-height: 1.8;239 color: var(--cyan);240 }241 242 .callout {243 border-left: 4px solid;244 padding: 15px;245 margin: 20px 0;246 border-radius: 6px;247 }248 249 .callout.tip {250 border-left-color: var(--green);251 background: rgba(0, 255, 136, 0.05);252 }253 254 .callout.warning {255 border-left-color: var(--yellow);256 background: rgba(255, 165, 0, 0.05);257 }258 259 .callout.insight {260 border-left-color: var(--cyan);261 background: rgba(0, 212, 255, 0.05);262 }263 264 .callout-title {265 font-weight: 700;266 margin-bottom: 8px;267 }268 269 .list-item {270 display: flex;271 gap: 12px;272 margin: 12px 0;273 padding: 12px;274 background: rgba(0, 212, 255, 0.05);275 border-left: 3px solid var(--cyan);276 border-radius: 4px;277 }278 279 .list-num {280 color: var(--orange);281 font-weight: 700;282 min-width: 30px;283 }284 285 table {286 width: 100%;287 border-collapse: collapse;288 margin: 20px 0;289 }290 291 th, td {292 padding: 12px;293 text-align: left;294 border: 1px solid rgba(0, 212, 255, 0.2);295 }296 297 th {298 background: rgba(0, 212, 255, 0.1);299 color: var(--cyan);300 font-weight: 700;301 }302 303 @media (max-width: 768px) {304 h1 { font-size: 1.8em; }305 .tabs { flex-direction: column; }306 .tab-btn { width: 100%; }307 .grid { grid-template-columns: 1fr; }308 }309 </style>310</head>311<body>312 <div class="container">313 <!-- MAIN DASHBOARD -->314 <div id="dashboard" class="dashboard active">315 <header>316 <h1>๐ง Complete Deep Learning & Computer Vision</h1>317 <p class="subtitle">Comprehensive Curriculum | Foundations to Advanced Applications</p>318 </header>319 320 <div style="text-align: center; margin-bottom: 40px;">321 <p style="color: var(--text-dim); font-size: 1.1em;">322 Master all aspects of deep learning and computer vision. 25+ modules covering neural networks, CNNs, object detection, GANs, and more.323 </p>324 </div>325 326 <div class="grid" id="modulesGrid"></div>327 </div>328 329 <!-- MODULES CONTAINER -->330 <div id="modulesContainer"></div>331 </div>332 333 <script>334 const modules = [335 // Module 1: Deep Learning Foundations336 {337 id: "nn-basics",338 title: "Introduction to Neural Networks",339 icon: "๐งฌ",340 category: "Foundations",341 color: "#0088ff",342 description: "Biological vs. Artificial neurons and network architecture"343 },344 {345 id: "perceptron",346 title: "The Perceptron",347 icon: "โ๏ธ",348 category: "Foundations",349 color: "#0088ff",350 description: "Single layer networks and their limitations"351 },352 {353 id: "mlp",354 title: "Multi-Layer Perceptron (MLP)",355 icon: "๐๏ธ",356 category: "Foundations",357 color: "#0088ff",358 description: "Hidden layers and deep architectures"359 },360 {361 id: "activation",362 title: "Activation Functions",363 icon: "โก",364 category: "Foundations",365 color: "#0088ff",366 description: "Sigmoid, ReLU, Tanh, Leaky ReLU, ELU, Softmax"367 },368 {369 id: "weight-init",370 title: "Weight Initialization",371 icon: "๐ฏ",372 category: "Foundations",373 color: "#0088ff",374 description: "Xavier, He, Random initialization strategies"375 },376 {377 id: "loss",378 title: "Loss Functions",379 icon: "๐",380 category: "Foundations",381 color: "#0088ff",382 description: "MSE, Binary Cross-Entropy, Categorical Cross-Entropy"383 },384 {385 id: "optimizers",386 title: "Optimizers",387 icon: "๐ฏ",388 category: "Training",389 color: "#00ff00",390 description: "SGD, Momentum, Adam, Adagrad, RMSprop"391 },392 {393 id: "backprop",394 title: "Forward & Backpropagation",395 icon: "โฌ
๏ธ",396 category: "Training",397 color: "#00ff00",398 description: "Chain rule and gradient computation"399 },400 {401 id: "regularization",402 title: "Regularization",403 icon: "๐ก๏ธ",404 category: "Training",405 color: "#00ff00",406 description: "L1/L2, Dropout, Early Stopping, Batch Norm"407 },408 {409 id: "batch-norm",410 title: "Batch Normalization",411 icon: "โ๏ธ",412 category: "Training",413 color: "#00ff00",414 description: "Stabilizing and speeding up training"415 },416 // Module 2: Computer Vision Fundamentals417 {418 id: "cv-intro",419 title: "CV Fundamentals",420 icon: "๐๏ธ",421 category: "Computer Vision",422 color: "#ff6b35",423 description: "Why ANNs fail with images, parameter explosion"424 },425 {426 id: "conv-layer",427 title: "Convolutional Layers",428 icon: "๐ผ๏ธ",429 category: "Computer Vision",430 color: "#ff6b35",431 description: "Kernels, filters, feature maps, stride, padding"432 },433 {434 id: "pooling",435 title: "Pooling Layers",436 icon: "๐ฆ",437 category: "Computer Vision",438 color: "#ff6b35",439 description: "Max pooling, average pooling, spatial reduction"440 },441 {442 id: "cnn-basics",443 title: "CNN Architecture",444 icon: "๐๏ธ",445 category: "Computer Vision",446 color: "#ff6b35",447 description: "Combining conv, pooling, and fully connected layers"448 },449 {450 id: "viz-filters",451 title: "Visualizing CNNs",452 icon: "๐",453 category: "Computer Vision",454 color: "#ff6b35",455 description: "What filters learn: edges โ shapes โ objects"456 },457 // Module 3: Advanced CNN Architectures458 {459 id: "lenet",460 title: "LeNet-5",461 icon: "๐ข",462 category: "CNN Architectures",463 color: "#ff00ff",464 description: "Classic digit recognizer (MNIST)"465 },466 {467 id: "alexnet",468 title: "AlexNet",469 icon: "๐",470 category: "CNN Architectures",471 color: "#ff00ff",472 description: "The breakthrough in deep computer vision (2012)"473 },474 {475 id: "vgg",476 title: "VGGNet",477 icon: "๐",478 category: "CNN Architectures",479 color: "#ff00ff",480 description: "VGG-16/19: Deep networks with small filters"481 },482 {483 id: "resnet",484 title: "ResNet",485 icon: "๐",486 category: "CNN Architectures",487 color: "#ff00ff",488 description: "Skip connections, solving vanishing gradients"489 },490 {491 id: "inception",492 title: "InceptionNet (GoogLeNet)",493 icon: "๐ฏ",494 category: "CNN Architectures",495 color: "#ff00ff",496 description: "1x1 convolutions, multi-scale feature extraction"497 },498 {499 id: "mobilenet",500 title: "MobileNet",501 icon: "๐ฑ",502 category: "CNN Architectures",503 color: "#ff00ff",504 description: "Depth-wise separable convolutions for efficiency"505 },506 {507 id: "transfer-learning",508 title: "Transfer Learning",509 icon: "๐",510 category: "CNN Architectures",511 color: "#ff00ff",512 description: "Fine-tuning and leveraging pre-trained models"513 },514 // Module 4: Object Detection & Segmentation515 {516 id: "localization",517 title: "Object Localization",518 icon: "๐",519 category: "Detection",520 color: "#00ff00",521 description: "Bounding boxes and classification together"522 },523 {524 id: "rcnn",525 title: "R-CNN Family",526 icon: "๐ฏ",527 category: "Detection",528 color: "#00ff00",529 description: "R-CNN, Fast R-CNN, Faster R-CNN"530 },531 {532 id: "yolo",533 title: "YOLO",534 icon: "โก",535 category: "Detection",536 color: "#00ff00",537 description: "Real-time object detection (v3, v5, v8)"538 },539 {540 id: "ssd",541 title: "SSD",542 icon: "๐",543 category: "Detection",544 color: "#00ff00",545 description: "Single Shot MultiBox Detector"546 },547 {548 id: "semantic-seg",549 title: "Semantic Segmentation",550 icon: "๐๏ธ",551 category: "Segmentation",552 color: "#00ff00",553 description: "Pixel-level classification (U-Net)"554 },555 {556 id: "instance-seg",557 title: "Instance Segmentation",558 icon: "๐ฅ",559 category: "Segmentation",560 color: "#00ff00",561 description: "Mask R-CNN and separate object instances"562 },563 {564 id: "face-recog",565 title: "Face Recognition",566 icon: "๐ค",567 category: "Segmentation",568 color: "#00ff00",569 description: "Siamese networks and triplet loss"570 },571 // Module 5: Generative Models572 {573 id: "autoencoders",574 title: "Autoencoders",575 icon: "๐",576 category: "Generative",577 color: "#ffaa00",578 description: "Encoder-decoder, latent space, denoising"579 },580 {581 id: "gans",582 title: "GANs (Generative Adversarial Networks)",583 icon: "๐ฎ",584 category: "Generative",585 color: "#ffaa00",586 description: "Generator vs. Discriminator, DCGAN"587 },588 {589 id: "diffusion",590 title: "Diffusion Models",591 icon: "๐",592 category: "Generative",593 color: "#ffaa00",594 description: "Foundation of Stable Diffusion and DALL-E"595 },596 // Additional Advanced Topics597 {598 id: "rnn",599 title: "RNNs & LSTMs",600 icon: "๐",601 category: "Sequence",602 color: "#ff6b35",603 description: "Recurrent networks for sequential data"604 },605 {606 id: "transformers",607 title: "Transformers",608 icon: "๐",609 category: "Sequence",610 color: "#ff6b35",611 description: "Attention mechanisms and modern architectures"612 },613 {614 id: "bert",615 title: "BERT & NLP Transformers",616 icon: "๐",617 category: "NLP",618 color: "#ff6b35",619 description: "Bidirectional transformers for language"620 },621 {622 id: "gpt",623 title: "GPT & Language Models",624 icon: "๐ฌ",625 category: "NLP",626 color: "#ff6b35",627 description: "Autoregressive models and text generation"628 },629 {630 id: "vit",631 title: "Vision Transformers (ViT)",632 icon: "๐จ",633 category: "Vision",634 color: "#ff6b35",635 description: "Transformers applied to image data"636 }637 ];638 639 function createModuleHTML(module) {640 return `641 <div class="module" id="${module.id}-module">642 <button class="btn-back" onclick="switchTo('dashboard')">โ Back to Dashboard</button>643 <header>644 <h1>${module.icon} ${module.title}</h1>645 <p class="subtitle">${module.description}</p>646 </header>647 648 <div class="tabs">649 <button class="tab-btn active" onclick="switchTab(event, '${module.id}-overview')">Overview</button>650 <button class="tab-btn" onclick="switchTab(event, '${module.id}-concepts')">Key Concepts</button>651 <button class="tab-btn" onclick="switchTab(event, '${module.id}-math')">Math</button>652 <button class="tab-btn" onclick="switchTab(event, '${module.id}-applications')">Applications</button>653 <button class="tab-btn" onclick="switchTab(event, '${module.id}-summary')">Summary</button>654 </div>655 656 <div id="${module.id}-overview" class="tab active">657 <div class="section">658 <h2>๐ Overview</h2>659 <p>Complete coverage of ${module.title.toLowerCase()}. Learn the fundamentals, mathematics, real-world applications, and implementation details.</p>660 <div class="info-box">661 <div class="box-title">Learning Objectives</div>662 <div class="box-content">663 โ Understand core concepts and theory<br>664 โ Master mathematical foundations<br>665 โ Learn practical applications<br>666 โ Implement and experiment667 </div>668 </div>669 </div>670 </div>671 672 <div id="${module.id}-concepts" class="tab">673 <div class="section">674 <h2>๐ฏ Key Concepts</h2>675 <p>Fundamental concepts and building blocks for ${module.title.toLowerCase()}.</p>676 <div class="callout insight">677 <div class="callout-title">๐ก Main Ideas</div>678 This section covers the core ideas you need to understand before diving into mathematics.679 </div>680 </div>681 </div>682 683 <div id="${module.id}-math" class="tab">684 <div class="section">685 <h2>๐ Mathematical Foundation</h2>686 <p>Rigorous mathematical treatment of ${module.title.toLowerCase()}.</p>687 <div class="formula">688 Mathematical formulas and derivations go here689 </div>690 </div>691 </div>692 693 <div id="${module.id}-applications" class="tab">694 <div class="section">695 <h2>๐ Real-World Applications</h2>696 <p>How ${module.title.toLowerCase()} is used in practice across different industries.</p>697 <div class="info-box">698 <div class="box-title">Use Cases</div>699 <div class="box-content">700 Common applications and practical examples701 </div>702 </div>703 </div>704 </div>705 706 <div id="${module.id}-summary" class="tab">707 <div class="section">708 <h2>โ
Summary</h2>709 <div class="info-box">710 <div class="box-title">Key Takeaways</div>711 <div class="box-content">712 โ Essential concepts covered<br>713 โ Mathematical foundations understood<br>714 โ Real-world applications identified<br>715 โ Ready for implementation716 </div>717 </div>718 </div>719 </div>720 </div>721 `;722 }723 724 function initDashboard() {725 const grid = document.getElementById("modulesGrid");726 const container = document.getElementById("modulesContainer");727 728 modules.forEach(module => {729 const card = document.createElement("div");730 card.className = "card";731 card.style.borderColor = module.color;732 card.onclick = () => switchTo(module.id + "-module");733 card.innerHTML = `734 <div class="card-icon">${module.icon}</div>735 <h3>${module.title}</h3>736 <p>${module.description}</p>737 <span class="category-label">${module.category}</span>738 `;739 grid.appendChild(card);740 741 const moduleHTML = createModuleHTML(module);742 container.innerHTML += moduleHTML;743 });744 }745 746 function switchTo(target) {747 document.querySelectorAll('.dashboard, .module').forEach(el => {748 el.classList.remove('active');749 });750 const elem = document.getElementById(target);751 if (elem) elem.classList.add('active');752 }753 754 function switchTab(e, tabId) {755 const module = e.target.closest('.module');756 if (!module) return;757 758 module.querySelectorAll('.tab').forEach(t => t.classList.remove('active'));759 module.querySelectorAll('.tab-btn').forEach(b => b.classList.remove('active'));760 761 const tab = document.getElementById(tabId);762 if (tab) tab.classList.add('active');763 e.target.classList.add('active');764 }765 766 initDashboard();767 </script>768</body>769</html>770 