AI, graphs and neural networks
Artificial intelligence
- AI builds systems that do tasks normally needing human intelligence — vision, speech, translation, driving.
- Most modern AI uses machine learning, and within it deep learning with neural networks.
- Many AI problems are searched on a graph.
What AI is
- Machine learning = algorithms that learn patterns from data instead of being programmed step by step.
- Deep learning uses neural networks with many layers — dominant since the 2010s.
- These let models learn straight from raw data (pixels, audio, text).
Practice
Machine learning means an algorithm that:
ML learns from data; deep learning is ML using multi-layer neural networks.
Graphs in AI
- Many AI problems sit on a graph — nodes (states/places) joined by edges (moves/relationships).
- Pathfinding: roads form a graph; shortest route via Dijkstra or A*.
- Game playing: each position is a node, each move an edge; minimax searches the game tree.
- Knowledge representation: a semantic network has concepts as nodes and relationships as edges. BFS and DFS are standard graph-search tools.
Practice
In AI, a graph consists of:
Graphs model states/places as nodes and moves/relationships as edges — used for pathfinding, game trees and knowledge.
Artificial neural networks
- An artificial neuron multiplies each input by a weight, adds them (with a bias), applies a non-linear activation function, and outputs the result.
- Neurons sit in an input layer, one or more hidden layers (where internal patterns are learned), and an output layer.
- Many hidden layers → a deep neural network; training it is deep learning.
Practice
An artificial neuron computes its output by:
Each input is weighted and summed with a bias, then passed through a non-linear activation function.
Practice
The hidden layers of a neural network:
Hidden layers build up internal representations; more of them makes the network "deep".
Practice
A neural network is called "deep" when it has:
Many hidden layers make a deep neural network; training one is deep learning.
You've got it
Key idea
- machine learning learns from data; deep learning uses multi-layer neural networks
- many AI problems are graph search (pathfinding, minimax game trees, semantic networks)
- a neuron = weighted sum + bias → activation function → output
- layers: input → hidden(s) → output; many hidden layers = deep