Machine learningLesson 1 of 2 in the course Neural networks

Neural Networks: Architectures, Training, History, and Applications

5 flashcards · 5 quiz questions · 5 match pairs · 5 fill-in sentences · English

Save course
Lesson progress
0 / 5

Your progress is kept in this browser only.Sign up to save it

Summary

This lesson introduces the basic components of an artificial neural network and explains how they work together to transform data.

An artificial neural network (ANN) is a computational model inspired loosely by biological neural networks. It is made of connected units called artificial neurons. A neuron receives numerical signals from other units, processes them, and produces a numerical output for connected neurons.

All flashcards

What is an artificial neural network?
A computational model made of connected artificial neurons that process numerical signals. Its connection weights are adjusted during training.
What is a connection weight?
A numerical value that determines how strongly a signal along a connection affects the receiving neuron.
What does an activation function do?
It transforms the weighted input, usually after a bias is added, into a neuron's output. Nonlinear activations enable more complex computations.
What are hidden layers?
Intermediate layers between the input and output layers. They transform signals and can develop increasingly abstract representations.
What makes a neural network deep?
A neural network is commonly called deep when it has at least two hidden layers.

Quiz questions

  1. What does a connection weight control in an artificial neural network?Answer: It scales the influence of an input signal on a receiving neuron.
  2. What is the role of an activation function?Answer: It maps a neuron's combined input to an output, often adding nonlinearity.
  3. What does backpropagation calculate during neural-network training?Answer: Gradients of the loss with respect to network parameters.
  4. What kind of feedback is provided in supervised learning?Answer: Paired inputs and desired outputs.
  5. How does attention help a transformer process a sequence?Answer: It weights information from different positions to model their relationships.

Based on the Wikipedia article Neural network (machine learning), licensed CC BY-SA 4.0. Adapted into a summary, flashcards and quizzes.

More in Machine learning

All Machine learning lessons
Machine learningAutoencoder Architectures, Training, Regularization, and Applications5 flashcards · 5 quiz questions · 4 gamesPlay free →Machine learningSupport Vector Machines: Margins, Kernels, Optimization, and Extensions5 flashcards · 5 quiz questions · 4 gamesPlay free →Machine learningNeural-Network Activation Functions: Properties and Families5 flashcards · 5 quiz questions · 4 gamesPlay free →Machine learningHierarchical Clustering: Linkage, Dendrograms, and Scalable Methods5 flashcards · 5 quiz questions · 4 gamesPlay free →