View markdown source on GitHub

Feedforward neural networks (FNN) Deep Learning - Part 1

Contributors

AvatarKaivan Kamali

Questions

Objectives

Requirements

last_modification Last modification: Jul 9, 2021

What is an artificial neural network?

Speaker Notes

What is an artificial neural network?


Artificial Neural Networks


Inspiration for neural networks

Sketch of a biological neuron and its components.


Celebral cortex


Celebral cortex


Perceptron

Neurons forming the input and output layers of a single layer feedforward neural network.


Learning in Perceptron


Limitations of Perceptron


Multi-layer FNN

Neurons forming the input, output, and hidden layers of a multi-layer feedforward neural network.


Activation functions

Table showing the formula, graph, derivative, and range of common activation functions.


Supervised learning


Classification problems

Three images illustrating binary, multiclass, and multilabel classifications and their label representation.


Output layer

Output layer (Continued)


Loss/Cost functions


Cross Entropy Loss/Cost functions

Cross Entropy loss function.

Cross Entropy cost function.


Quadratic Loss/Cost functions

Quadratic loss function.

Quadratic cost function.


Backpropagation (BP) learning algorithm


Backpropagation error

Backpropagation error.


Backpropagation formulas

Backpropagation formulas.


Types of Gradient Descent


Vanishing gradient problem


Car purchase price prediction


For references, please see tutorial’s References section


Screenshot of the gtn stats page with 21 topics, 170 tutorials, 159 contributors, 16 scientific topics, and a growing community.

Speaker Notes


Getting Help

Speaker Notes


Join an event

Event schedule.

Speaker Notes


Thank you!

This material is the result of a collaborative work. Thanks to the Galaxy Training Network and all the contributors! Galaxy Training Network This material is licensed under the Creative Commons Attribution 4.0 International License.