Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Genetic Algorithms
Search
Luke Williams
July 16, 2020
Science
0
81
Genetic Algorithms
Solving problems the natural way
Luke Williams
July 16, 2020
Tweet
Share
More Decks by Luke Williams
See All by Luke Williams
Useful Mental Models For Product Engineers
redroot
0
120
Unity Talk
redroot
0
37
Neural Networks - a brief introduction by a fan
redroot
0
430
Web Accessibility in 2019
redroot
0
460
redux-saga
redroot
0
560
Redis - Lightning Talk @ RefME
redroot
0
720
Wordpress Multitenancy
redroot
0
1.5k
Embracing the Customizer
redroot
2
750
Other Decks in Science
See All in Science
Symfony Console Facelift
chalasr
2
460
科学で迫る勝敗の法則(電気学会・SICE若手セミナー講演 2024年12月) / The principle of victory discovered by science (Lecture for young academists in IEEJ-SICE))
konakalab
0
120
「美は世界を救う」を心理学で実証したい~クラファンを通じた新しい研究方法
jimpe_hitsuwari
1
160
データベース15: ビッグデータ時代のデータベース
trycycle
PRO
0
330
凸最適化からDC最適化まで
santana_hammer
1
280
Transport information Geometry: Current and Future II
lwc2017
0
180
mathematics of indirect reciprocity
yohm
1
170
コンピュータビジョンによるロボットの視覚と判断:宇宙空間での適応と課題
hf149
1
310
傾向スコアによる効果検証 / Propensity Score Analysis and Causal Effect Estimation
ikuma_w
0
130
機械学習 - K-means & 階層的クラスタリング
trycycle
PRO
0
1k
学術講演会中央大学学員会府中支部
tagtag
0
300
統計的因果探索: 背景知識とデータにより因果仮説を探索する
sshimizu2006
4
990
Featured
See All Featured
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
51
5.6k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
36
2.5k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
284
13k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
53
2.9k
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.6k
Navigating Team Friction
lara
189
15k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
For a Future-Friendly Web
brad_frost
179
9.9k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
Agile that works and the tools we love
rasmusluckow
330
21k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Transcript
Genetic Algorithms Solving problems the natural way
Making Decisions - go to the market?
Making decisions - which car to buy?
Making decisions - mimic art? wizardry! 50 semi transparent shapes
Mona Lisa
Designing a car by mistake
Under the hood Candidates Genome Fitness List of candidate solutions
to the problem. “Genetic” code for each candidate that describes the characteristics that will “evolve” How to determine the “fittest” candidates
Under the hood Candidates Genome Fitness 14aF2bdz12 9avg2bc1sd 44bg92jcks 120m
90m 1m
Under the hood 14aF2bdz12 shape wheel size wheel position wheel
density chasis density
Under the hood Candidates Genome Fitness 14aF2bdz12 14aG2bdz12 25aF2cdz12 ?
? ?
Under the hood Candidates Genome Fitness 14aF2bdz12 14aF2bc1td ? ?
? 9avg2bc1sd
Under the hood Clone/mate to build the next generation Find
the fittest candidate(s) Randomly mutate the genome Build all candidates in generation
In the wild
In the wild
In the wild - Flight / train scheduling - Timetabling
- e.g at a school - Factory floor design - Mechanical engineering - Music production - Financial modelling - Code-breaking - Artificial Intelligence
Genetic Algorithms Solving problems the natural way