Intro to Neural Networks (Brilliant.org)
Last Updated on June 9, 2020 by Editorial Team
Author(s): Alison Sin
These are the notes I’ve taken while going through this course at Brilliant.org. 🙂 since a premium membership might not be universally accessible and they did an outstanding job explaining the concept in simple terms, I decided to share some insights 😊
Note: All credits go to Brilliant.org!
A. Why Artificial Neural Networks (ANNs)?
Because some problems X be solved with programming.
e.g. a vision problem: object recognition [classifying simple objects]
→ the main difference: different number of corners
B. What is an ANN?
An ANN is made up of ANs (artificial neurons).
Features of AN:
i) follow the rules mechanically from input to output
ii) learn by feedback reinforcement:
1. ANN is fed with input → make the best guess
2. if correct → nothing happens VS
If wrong → adjust the internal configuration to change computation
- Types: 1. Binary Neurons, 2. Sigmoid, 3. Identity
- Act as: 1) classifiers → 2) predictors
Can adjust: 1) bias (threshold), 2) weights (influence)
- Binary Neurons (~ Decision Box)
a) perform “AND,” “OR” by changing the bias
e.g., with two inputs (I1, I2)
if I1 + I2 ≥ bias → “ON”
b) can perform “XOR” → by introducing -ve inputs
Intro to Neural Networks (Brilliant.org) was originally published in Towards AI — Multidisciplinary Science Journal on Medium, where people are continuing the conversation by highlighting and responding to this story.
Published via Towards AI