Differences between AI, ML, DL

Artificial Intelligence (AI)

AI is the broadest concept of machines being able to carry out tasks in a way that we would consider “smart.” It encompasses any technique that enables computers to mimic human intelligence.

Key characteristics:

• Encompasses all techniques enabling machines to simulate human intelligence
• Includes rule-based systems, expert systems, and more
• Focuses on reasoning, problem-solving, natural language processing, and perception

Machine Learning (ML)

ML is a subset of AI that focuses on algorithms that allow machines to learn patterns from data and improve their performance over time without being explicitly programmed for every task.

Key characteristics:

• Uses statistical techniques to learn from data
• Requires training data to build predictive models
• Includes supervised, unsupervised, and reinforcement learning

Deep Learning (DL)

DL is a specialized subset of ML that uses neural networks with many layers (deep neural networks) to model complex patterns in large amounts of data.

Key characteristics:

• Relies on multi-layered neural networks
• Excels in tasks such as image and speech recognition
• Requires large datasets and significant computational power

AI Example (Rule-Based System)

// Simple AI rule-based decision
function aiDecision(input) {
    if (input === 'rainy') return 'Take an umbrella';
    else if (input === 'sunny') return 'Wear sunglasses';
    else return 'Check weather forecast';
}
console.log(aiDecision('rainy')); // Output: Take an umbrella

ML Example (Supervised Learning with Scikit-learn)

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier

data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.3, random_state=42)

model = RandomForestClassifier()
model.fit(X_train, y_train)
print("Accuracy:", model.score(X_test, y_test))

DL Example (Simple Neural Network with TensorFlow/Keras)

import tensorflow as tf
from tensorflow.keras import layers, models

model = models.Sequential([
    layers.Dense(64, activation='relu', input_shape=(100,)),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# model.fit(X_train, y_train, epochs=10)  # Assuming data is preprocessed