Neural Networks Overview

Front

What represents the strength of connections between neurons?

Back

𝑤𝑖

Front

How is the amount of information received by a neuron calculated?

Back

The product 𝑤𝑖𝑥𝑖

Front

What is the formula for the total contributions to a neuron?

Back

𝑏 + σ𝑖 𝑤𝑖𝑥𝑖

Front

What is the purpose of the non-linear activation function 𝑓 in a neuron?

Back

To produce the output 𝑓(𝑏 + σ𝑖 𝑤𝑖𝑥𝑖) which is passed to other neurons.

Front

What is a neural network defined as?

Back

A massively parallel distributed processor made up of simple processing units.

Front

What are the two respects in which a neural network resembles the brain?

Back

1. Knowledge is acquired from the environment through learning. 2. Interneuron connection strengths (synaptic weights) store acquired knowledge.

Front

What is the procedure used to perform the learning process in neural networks called?

Back

Learning Algorithm

Front

What is the function of the Learning Algorithm in a neural network?

Back

To modify the synaptic weights of the network in an orderly fashion to attain desired objectives.

Front

Can a neural network modify its own topology?

Back

Yes, it can modify its topology motivated by the fact that neurons can die and new synaptic connections can grow.

Front

What are some alternative names for neural networks?

Back

Neurocomputers, connectionist networks, parallel distributed processors.