Modelling Brain and Mind


Pregunta 1 of 1

  Tiempo Restante


Match word to definition

Haga coincidir el texto (haga clic y arrastre)   


Empareja el texto


Algorithmic complexity

Logical depth


Fractal dimension

Synthetic psychology

Braitenberg vehicle

Artificial neural network


Gradient descent

Global minimum

Local minimum


Supervised learning

The Rescorla-Wagner model

The Delta-rule


Decision boundary

Linear separability

Exclusive-OR problem (XOR problem)




Hacer clic y arrastrar

How difficult it is to deduce the shortest possbile algorithm required to generate a sequence.

The order in which associations are learn between stimulus (cue) and a reinforcer (reward/punishment) matters

This measures the length of the shortest computer program required to generate a particular sequence of symbols.

Comes from neural network research and was discovered as a way of modifying the synaptic weights of an artificial neuron

The behaviour of a circuit that controls its output to reduce the differences between its output and target ouput

A property of complex systems, such as a recurrent neural network. It's a set of states that a system can adopt where one state always leadds to a second state, to a third state etc.

A straight line in the input space, separated positive outputs from negative outputs of a neuron

A branch of maths concerned with finding and using the derivative of a function

Solution corresponds to drawing a straight line in a graph, that separates one category of ouputs from another

The number of iterations of the shortest algorithm required to generate a sequence.

A motor whose output value is calculated by multiplying each wire by the corresponding sensor reading and adding them together

Synthesizing the behabiourof complex systems like the brain and mind by exploring how simple models of biological processes interact with an environment

A set of artificial neurons whose outputs are connected to the inputs of others

A method for finding the valleys in a function (the lowest point, where the error is lowest)

Discovered as a way of describing how associative strengths should change during a classical conditioning task

Spontaneous emergence of global order from a system of individuals interacting according to simple rules in the absence of a supervisor

A ratio comparing how detail ina pattern (a fractal pattern) changes with the scale at which it is measured

The value of the parameter that generates the lowest possible error

A secondary valley with a higher error where the algorithm will stop before the global minimum

A series of instructions that should be followed

A supervised learning algorithm for updating the synaptic weights in a neural network

Presenting a network with examples of input patterns along with information about what the correct outputs should be in response to those inputs

Should generate an output of 1 when either the first or the second input is 1 and it should generate an output of 0 when both inputs are 1 or 0