AI Terms

Question 1

What is a neural network

Answer 1

A method in AI that teaches computers to process data in a way that us inspired by the human brain

Question 2

What type of ML process is a neural network

Answer 2

Deep Learning

Question 3

What does deep learning use?

Answer 3

interconnected nodes or neurons in a layered structure that resembles the human brain

Question 4

Why are neural networks important?

Answer 4

Neural networks can help computers make intelligent decisions with limited human assistance
They can learn and model the relationships between input and output data that are nonlinear and complex

Question 5

What is an RNN

Answer 5

Recurrent Neural Network

Question 5

What is a CNN

Answer 5

Convolutional Neural Network

Question 5

What is inference?

Answer 5

the process that a trained machine learning model* uses to draw conclusions from brand-new data.

Question 6

What is an Algorithm?

Answer 6

A set of instructions used to perform tasks (such as calculations and data analysis) usually using a computer or another smart device.

Question 6

What is SDR

Answer 6

Signal to distortion ratio

Question 7

What is the magnitude spectrum

Answer 7

The Magnitude Spectrum refers to the representation of the magnitude of the Fourier transform of a signal, where it is an even function of the frequency variable. It is a key component in analyzing the frequency content of signals in Computer Science.

Question 7

What is an ANN

Answer 7

Artificial Neural network

Question 8

What does spectrum mean?

Answer 8

The word “spectrum” is loosely used to mean different aspects of the frequency representation.

Question 9

what does temporal mean?

Answer 9

Relating to time (think tempo)

Question 10

What does an ANN consist of?

Answer 10

ANNs consist of many perceptrons

Question 11

what is a perceptron?

Answer 11

Perceptron - In its simplest form, a perceptron is a function that takes two inputs, multiplies them by two random weights, adds them together with a bias value, passes the results through an activation function and prints the results. The weights and bias values, which are adjustable, define the outcome of the perceptron given two specific input values.

Question 12

What’s the difference between a CNN and an RNN?

Answer 12

CNNs are commonly used to solve problems involving spatial data, such as images. RNNs are better suited to analyzing temporal and sequential data, such as text or videos

Question 13

What are the types of neural networks?

Answer 13

Feedforward neural networks
Backpropagation algorithm
Convolutional neural networks

Question 14

What is a loss function?

Answer 14

AKA an cost function. A function that maps an event or values of one or more variables onto a real number intuitively representing some “cost” associated with the event.Optimizing seeks to minimize a loss function.