ducoterra
e55534b0d5
All checks were successful
Build and Push Container / build-and-push (push) Successful in 13s
191 lines
8.3 KiB
HTML
191 lines
8.3 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 Terminology - Cheat Sheet</title>
|
|
<link rel="stylesheet" href="../css/style.css">
|
|
</head>
|
|
<body>
|
|
|
|
<nav>
|
|
<div class="nav-inner">
|
|
<a href="../index.html" class="nav-brand">AI Cheat Sheet</a>
|
|
<div class="nav-links">
|
|
<a href="terminology.html" class="active">Terminology</a>
|
|
<a href="techniques.html">Techniques</a>
|
|
<a href="use-cases.html">Use Cases</a>
|
|
<a href="model-types.html">Model Types</a>
|
|
<a href="prompts.html">Prompt Guide</a>
|
|
<a href="math.html">Math & Concepts</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 Terminology</h1>
|
|
<p>Essential terms every AI learner should know.</p>
|
|
</div>
|
|
|
|
<div class="container">
|
|
|
|
<h2 class="section-title">Machine Learning Basics</h2>
|
|
<div class="def-card">
|
|
<span class="category">ML</span>
|
|
<h3>Machine Learning (ML)</h3>
|
|
<p>A subset of AI where systems learn patterns from data to make decisions or predictions without being explicitly programmed for each task.</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">ML</span>
|
|
<h3>Supervised Learning</h3>
|
|
<p>Training a model on labeled data — each example has an input and a known correct output. The model learns to map inputs to outputs.</p>
|
|
<div class="example"><strong>Example:</strong> Training on emails labeled "spam" or "not spam" to build a spam filter.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">ML</span>
|
|
<h3>Unsupervised Learning</h3>
|
|
<p>Training on unlabeled data — the model finds hidden patterns or groupings on its own.</p>
|
|
<div class="example"><strong>Example:</strong> Grouping customers by purchasing behavior without pre-defined categories.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">ML</span>
|
|
<h3>Reinforcement Learning</h3>
|
|
<p>An agent learns by interacting with an environment, receiving rewards for good actions and penalties for bad ones, optimizing for maximum cumulative reward.</p>
|
|
<div class="example"><strong>Example:</strong> An AI learning to play chess by playing millions of games against itself.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">ML</span>
|
|
<h3>Overfitting</h3>
|
|
<p>When a model learns the training data too well — including noise and outliers — and performs poorly on new, unseen data.</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">ML</span>
|
|
<h3>Underfitting</h3>
|
|
<p>When a model is too simple to capture the patterns in the data, performing poorly on both training and test data.</p>
|
|
</div>
|
|
|
|
<h2 class="section-title">Natural Language Processing</h2>
|
|
<div class="def-card">
|
|
<span class="category">NLP</span>
|
|
<h3>NLP (Natural Language Processing)</h3>
|
|
<p>A field of AI focused on enabling computers to understand, interpret, and generate human language.</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">NLP</span>
|
|
<h3>Token</h3>
|
|
<p>The smallest unit of text a model processes. Tokens can be words, subwords, or characters. A single word may be split into multiple tokens.</p>
|
|
<div class="example"><strong>Example:</strong> "unhappiness" might become ["un", "happiness"] — 2 tokens.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">NLP</span>
|
|
<h3>Embedding</h3>
|
|
<p>A numerical representation of text (or other data) in a continuous vector space, where similar items are closer together.</p>
|
|
<div class="example"><strong>Example:</strong> "king", "queen", "man", "woman" are embedded so that queen - woman + man ≈ king.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">NLP</span>
|
|
<h3>Context Window</h3>
|
|
<p>The maximum number of tokens a model can process at once — both input and output combined.</p>
|
|
<div class="example"><strong>Example:</strong> A 128K context window means the model can read ~100,000 words in a single prompt.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">NLP</span>
|
|
<h3>Paraphrasing</h3>
|
|
<p>Restating text in different words while preserving the original meaning. LLMs excel at this task.</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">NLP</span>
|
|
<h3>Sentiment Analysis</h3>
|
|
<p>Determining the emotional tone behind text — positive, negative, or neutral.</p>
|
|
<div class="example"><strong>Example:</strong> "This product is amazing!" → Positive</div>
|
|
</div>
|
|
|
|
<h2 class="section-title">Model Concepts</h2>
|
|
<div class="def-card">
|
|
<span class="category">Model</span>
|
|
<h3>LLM (Large Language Model)</h3>
|
|
<p>A neural network with billions of parameters trained on massive text corpora to understand and generate human language. Examples: GPT-4, Claude, Gemini, Llama.</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">Model</span>
|
|
<h3>Pre-trained Model</h3>
|
|
<p>A model that has already been trained on a large dataset and can be used as-is or fine-tuned for specific tasks.</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">Model</span>
|
|
<h3>Fine-tuning</h3>
|
|
<p>Taking a pre-trained model and continuing to train it on a smaller, task-specific dataset to adapt its behavior.</p>
|
|
<div class="example"><strong>Example:</strong> Fine-tuning GPT-4 on medical texts so it answers healthcare questions more accurately.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">Model</span>
|
|
<h3>Parameters</h3>
|
|
<p>The internal variables of a model that are adjusted during training. More parameters generally mean greater capacity to learn complex patterns.</p>
|
|
<div class="example"><strong>Example:</strong> GPT-4 is estimated to have trillions of parameters.</div>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">Model</span>
|
|
<h3>Inference</h3>
|
|
<p>The process of using a trained model to generate outputs for new inputs (as opposed to training the model).</p>
|
|
</div>
|
|
<div class="def-card">
|
|
<span class="category">Model</span>
|
|
<h3>Weights</h3>
|
|
<p>The numerical values learned during training that determine how input signals are transformed as they pass through the network.</p>
|
|
</div>
|
|
|
|
<h2 class="section-title">Common Acronyms</h2>
|
|
<table class="glossary-table">
|
|
<thead>
|
|
<tr><th>Acronym</th><th>Meaning</th></tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr><td>AI</td><td>Artificial Intelligence</td></tr>
|
|
<tr><td>ML</td><td>Machine Learning</td></tr>
|
|
<tr><td>DL</td><td>Deep Learning</td></tr>
|
|
<tr><td>NLP</td><td>Natural Language Processing</td></tr>
|
|
<tr><td>LLM</td><td>Large Language Model</td></tr>
|
|
<tr><td>RLHF</td><td>Reinforcement Learning from Human Feedback</td></tr>
|
|
<tr><td>RAG</td><td>Retrieval-Augmented Generation</td></tr>
|
|
<tr><td>API</td><td>Application Programming Interface</td></tr>
|
|
<tr><td>SFT</td><td>Supervised Fine-Tuning</td></tr>
|
|
<tr><td>PoC</td><td>Proof of Concept</td></tr>
|
|
<tr><td>GAN</td><td>Generative Adversarial Network</td></tr>
|
|
<tr><td>CNN</td><td>Convolutional Neural Network</td></tr>
|
|
<tr><td>AGI</td><td>Artificial General Intelligence</td></tr>
|
|
<tr><td>STT / ASR</td><td>Speech-to-Text / Automatic Speech Recognition</td></tr>
|
|
<tr><td>TTS</td><td>Text-to-Speech</td></tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
<footer>AI Cheat Sheet — A learning reference for artificial intelligence</footer>
|
|
|
|
</body>
|
|
</html>
|