Module 8: Mind as Network

Emergence

The arising of novel and complex properties or behaviors in a system from the interactions of its simpler components.

Connectionism

A computational approach to cognition that models mental processes as the emergent activity of interconnected networks of simple units.

Parallel Processing

The ability of a system to perform multiple computations or processes simultaneously.

Distributed Representation

A way of representing information where a concept is represented by a pattern of activation across multiple units in a network.

Neural Networks

Computational models inspired by biological neural networks consisting of interconnected nodes that process signals.

Hebbian Learning

A learning rule stating that the connection strength between two neurons increases if they are active simultaneously.

Backpropagation

an algorithm in artificial neural networks that trains the network by adjusting its weights and biases. it calculates the error at the output and works backwards layer by layer in order to minimize loss

100-Step Constraint

most mental processes can be explained through roughly 100 sequential processing steps. Although numerous neurons can be activated in parallel, the overall processing time for basic cognitive functions is limited

Graceful Degradation

The ability of a system to maintain performance even when parts are damaged or removed.

One-off Learning

The capacity to learn a new concept after a single exposure, posing challenges for many connectionist models.