184 lines
8.5 KiB
HTML
184 lines
8.5 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="en">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
<title>AI Cheat Sheet</title>
|
||
<link rel="stylesheet" href="css/style.css">
|
||
</head>
|
||
<body>
|
||
|
||
<nav>
|
||
<div class="nav-inner">
|
||
<a href="/" class="nav-brand active">AI Cheat Sheet</a>
|
||
<div class="nav-links">
|
||
<a href="/pages/terminology.html">Terminology</a>
|
||
<a href="/pages/techniques.html">Techniques</a>
|
||
<a href="/pages/use-cases.html">Use Cases</a>
|
||
<a href="/pages/model-types.html">Model Types</a>
|
||
<a href="/pages/prompts.html">Prompt Guide</a>
|
||
<a href="/pages/math.html">Math & Concepts</a>
|
||
<a href="/pages/chat.html">Chat</a>
|
||
</div>
|
||
<button class="dark-toggle" id="darkToggle" aria-label="Toggle dark mode">🌙</button>
|
||
</div>
|
||
</nav>
|
||
|
||
<script>
|
||
(function(){
|
||
var btn = document.getElementById('darkToggle');
|
||
var saved = localStorage.getItem('theme');
|
||
if(saved === 'dark' || (!saved && window.matchMedia('(prefers-color-scheme: dark)').matches)){
|
||
document.documentElement.setAttribute('data-theme','dark');
|
||
btn.textContent = '☀️';
|
||
}
|
||
btn.addEventListener('click', function(){
|
||
var isDark = document.documentElement.getAttribute('data-theme') === 'dark';
|
||
if(isDark){
|
||
document.documentElement.removeAttribute('data-theme');
|
||
btn.textContent = '🌙';
|
||
localStorage.setItem('theme','light');
|
||
} else {
|
||
document.documentElement.setAttribute('data-theme','dark');
|
||
btn.textContent = '☀️';
|
||
localStorage.setItem('theme','dark');
|
||
}
|
||
});
|
||
})();
|
||
</script>
|
||
|
||
<div class="hero">
|
||
<h1>AI Cheat Sheet</h1>
|
||
<p>Your quick reference for artificial intelligence terminology, techniques, and real-world applications.</p>
|
||
</div>
|
||
|
||
<div class="container">
|
||
<h2 class="section-title">Browse Topics</h2>
|
||
<div class="cards">
|
||
<a href="/pages/terminology.html" class="card-link">
|
||
<div class="card">
|
||
<h3>📖 Terminology</h3>
|
||
<p>Key AI terms from ML and NLP — supervised learning, fine-tuning, tokens, embeddings, and more.</p>
|
||
</div>
|
||
</a>
|
||
<a href="/pages/techniques.html" class="card-link">
|
||
<div class="card">
|
||
<h3>⚙️ Techniques</h3>
|
||
<p>How AI models are trained and improved — backpropagation, RLHF, quantization, RAG, and more.</p>
|
||
</div>
|
||
</a>
|
||
<a href="/pages/use-cases.html" class="card-link">
|
||
<div class="card">
|
||
<h3>🎯 Use Cases</h3>
|
||
<p>Where AI is used in the real world — healthcare, finance, creative work, customer support, and more.</p>
|
||
</div>
|
||
</a>
|
||
<a href="/pages/model-types.html" class="card-link">
|
||
<div class="card">
|
||
<h3>🤖 Model Types</h3>
|
||
<p>LLMs, diffusion models, CNNs, GANs, transformers, and other AI architectures explained.</p>
|
||
</div>
|
||
</a>
|
||
<a href="/pages/prompts.html" class="card-link">
|
||
<div class="card">
|
||
<h3>✍️ Prompt Engineering</h3>
|
||
<p>How to write effective prompts — zero-shot, few-shot, chain-of-thought, and structured prompts.</p>
|
||
</div>
|
||
</a>
|
||
<a href="/pages/math.html" class="card-link">
|
||
<div class="card">
|
||
<h3>📐 Math & Concepts</h3>
|
||
<p>Underlying concepts — loss functions, attention, temperature, perplexity, and accuracy metrics.</p>
|
||
</div>
|
||
</a>
|
||
</div>
|
||
|
||
<h2 class="section-title">Quick Start</h2>
|
||
<div class="def-card">
|
||
<span class="category">Core Concept</span>
|
||
<h3>What is Artificial Intelligence?</h3>
|
||
<p>AI refers to computer systems designed to perform tasks that normally require human intelligence — including learning, reasoning, problem-solving, perception, and language understanding. Modern AI is powered by machine learning, where models learn patterns from data rather than following explicit rules.</p>
|
||
</div>
|
||
<div class="def-card">
|
||
<span class="category">Quick Fact</span>
|
||
<h3>LLM vs Traditional ML</h3>
|
||
<p>Traditional ML models are built for one specific task (e.g., classify spam). Large Language Models are general-purpose — trained on massive text corpora to understand and generate human language across countless tasks.</p>
|
||
</div>
|
||
|
||
<h2 class="section-title">Interactive</h2>
|
||
<div class="ask-question-section">
|
||
<div class="ask-question-box">
|
||
<h3>💬 Ask a Question</h3>
|
||
<p style="color: var(--pink-700); font-size: 0.95rem; margin-bottom: 1rem;">Ask anything about AI — terminology, concepts, techniques, or real-world applications. Powered by your configured LLM.</p>
|
||
<div class="ask-question-input-row">
|
||
<input class="ask-question-input" id="askInput" placeholder="Ask me anything about AI..." />
|
||
<button class="llm-btn" onclick="askQuestion()" style="padding: 0.6rem 1.5rem;"><span class="icon">Send</span></button>
|
||
</div>
|
||
<div class="ask-question-answer" id="askAnswer"></div>
|
||
</div>
|
||
</div>
|
||
<a href="/pages/chat.html" class="card-link" style="margin-top: 1.5rem; display: block;">
|
||
<div class="card">
|
||
<h3>💬 Full Chat</h3>
|
||
<p>Try AI right now — ask questions, brainstorm ideas, get explanations, or just experiment. Powered by a real LLM API.</p>
|
||
</div>
|
||
</a>
|
||
</div>
|
||
|
||
<footer>AI Cheat Sheet — A learning reference for artificial intelligence</footer>
|
||
|
||
<script src="lib/llm.js"></script>
|
||
<script>
|
||
(function(){
|
||
function askQuestion() {
|
||
var input = document.getElementById('askInput');
|
||
var answer = document.getElementById('askAnswer');
|
||
var text = input.value.trim();
|
||
if (!text) return;
|
||
|
||
answer.classList.add('visible');
|
||
answer.innerHTML = '<span class="llm-loading">Thinking...</span>';
|
||
|
||
var cheatSheetContext = `You are an AI educator answering questions based on this cheat sheet content:
|
||
|
||
TERMINOLOGY: Machine Learning (ML), Supervised Learning, Unsupervised Learning, Reinforcement Learning, Overfitting, Underfitting, NLP, Token, Embedding, Context Window, Paraphrasing, Sentiment Analysis, LLM, Pre-trained Model, Fine-tuning, Parameters, Inference, Weights. Acronyms: AI, ML, DL, NLP, LLM, RLHF, RAG, API, SFT, PoC, GAN, CNN, AGI, STT/ASR, TTS.
|
||
|
||
TECHNIQUES: Backpropagation, Epoch, Batch Size, Learning Rate, Transfer Learning, Data Augmentation, RLHF, SFT, Prompt Tuning, LoRA, Quantization, Distillation, Speculative Decoding, RAG, Agent/Tool Use, Chain-of-Thought.
|
||
|
||
USE CASES: Content Generation, Image Generation, Video & Audio, Summarization, Code Generation, Debugging & Review, Documentation, Code Translation, Chatbots & Assistants, Data Analysis, Research & Search, Translation, Email & Meeting Assistants, Document Processing, Healthcare, Finance, Automotive, Education, Manufacturing, Legal.
|
||
|
||
MODEL TYPES: LLMs (GPT-4, Claude, Gemini, Llama, Mistral), Encoder-Only (BERT, RoBERTa), Decoder-Only (GPT, Claude, Llama), Encoder-Decoder (T5, BART), CNN (ResNet, EfficientNet), ViT (CLIP, DINOv2), Diffusion (Stable Diffusion, DALL-E), GAN (StyleGAN), VQ-VAE, Flow Models, RNN/LSTM, MoE, Retrieval Models, SLMs (Phi-3, Gemma).
|
||
|
||
PROMPT ENGINEERING: Zero-Shot, Few-Shot, Chain-of-Thought, Role Prompting, Structured Output, Self-Consistency, ReAct. Tips: Be specific, use delimiters, provide context, iterate.
|
||
|
||
MATH & CONCEPTS: Attention, Self-Attention, Multi-Head Attention, Positional Encoding, FFN, Layer Norm, Loss Function, Gradient Descent, Adam, Gradient, Regularization, Batch Norm, Temperature, Top-K, Top-P, Greedy Decoding, Beam Search, Logits, Perplexity, Accuracy, Precision & Recall, F1 Score, BLEU/ROUGE, TPS. Formulas: Attention=softmax(QKᵀ/√dₖ)V, Cross-Entropy=-Σyᵢlog(pᵢ), Softmax=eˣⁱ/Σeˣʲ, ReLU=max(0,x), LayerNorm=(x-μ)/σ×γ+β, F1=2×(P×R)/(P+R), Perplexity=2^(cross-entropy).`;
|
||
|
||
var messages = [
|
||
{ role: 'system', content: 'You are a helpful AI educator answering questions based on an AI cheat sheet. Use the context below to provide accurate, concise answers. If a question is outside the cheat sheet scope, say so but try to help anyway. Keep answers to 2-4 short paragraphs. Use formatting like bold text and code blocks where helpful.' },
|
||
{ role: 'user', content: cheatSheetContext + '\n\nQuestion: ' + text }
|
||
];
|
||
|
||
LLM.chatWithHistory('askAnswer', messages)
|
||
.then(function() {
|
||
answer.innerHTML = answer.innerHTML.replace('<span class="llm-loading">Thinking...</span>', '');
|
||
})
|
||
.catch(function() {});
|
||
}
|
||
|
||
var askInput = document.getElementById('askInput');
|
||
if (askInput) {
|
||
askInput.addEventListener('keydown', function(e) {
|
||
if (e.key === 'Enter') {
|
||
e.preventDefault();
|
||
askQuestion();
|
||
}
|
||
});
|
||
}
|
||
|
||
window.askQuestion = askQuestion;
|
||
})();
|
||
</script>
|
||
|
||
</body>
|
||
</html>
|