SUL Topic 6 - Neural Network Flashcards

1
Q

Neural Network

A

A computational model that mimics the structure and function of the human nervous system

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Biological Neuron Components

A

Dendrites, cell body, and axons

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Perceptron

A

Basic unit of an artificial neural network that takes multiple inputs and produces a single output

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Weight

A

Value assigned to each input representing its importance in the neural network

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Activation Function

A

Determines the output of a neural network node based on the weighted sum of inputs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Three main layers of a neural network

A

Input layer
hidden layers
output layer

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Deep Learning

A

Term used when a neural network has multiple hidden layers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Threshold Function

A

Activation function that outputs 0 or 1 based on a threshold

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Sigmoid Function

A

Activation function that outputs values between 0 and 1, useful for probability predictions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

ReLU

A

Activation function that outputs the input if positive, otherwise 0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Forward Propagation

A

Process of feeding inputs through the network to generate an output

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Back Propagation

A

Method to adjust weights by propagating errors backward from output to input layer

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Gradient Descent

A

Optimization technique used to minimize the cost function in neural networks

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Stochastic Gradient Descent

A

Updates weights using a single sample at a time, speeding up convergence for large datasets

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Supervised Learning

A

Training with input-output pairs to minimize error between predicted and actual outputs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Unsupervised Learning

A

Network classifies input data without predefined labels

17
Q

Reinforcement Learning

A

Network learns by receiving feedback on actions, adjusting strategy to maximize rewards

18
Q

Offline Learning

A

Weight adjustments made after processing the entire training set

19
Q

Online Learning

A

Weight adjustments made after processing each individual training example

20
Q

Training Set

A

Dataset used to train the network

21
Q

Validation Set

A

Dataset used to fine-tune network parameters

22
Q

Test Set

A

Dataset used to evaluate network performance on unseen data

23
Q

Applications of Neural Networks

A

Stock market prediction
weather forecasting
medical diagnosis
image and speech recognition