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
Neural networks on your phone
Search
Alejandro Isaza
August 02, 2016
Programming
0
47
Neural networks on your phone
Slides for technical lightning talk on neural networks running on portable devices.
Alejandro Isaza
August 02, 2016
Tweet
Share
Other Decks in Programming
See All in Programming
The Past, Present, and Future of Enterprise Java
ivargrimstad
0
140
CSC305 Lecture 05
javiergs
PRO
0
210
kiroとCodexで最高のSpec駆動開発を!!数時間で web3ネイティブなミニゲームを作ってみたよ!
mashharuki
0
520
バッチ処理を「状態の記録」から「事実の記録」へ
panda728
PRO
0
160
uniqueパッケージの内部実装を支えるweak pointerの話
magavel
0
1k
CSC509 Lecture 04
javiergs
PRO
0
300
Flutterで分数(Fraction)を表示する方法
koukimiura
0
130
3年ぶりにコードを書いた元CTOが Claude Codeと30分でMVPを作った話
maikokojima
0
320
はじめてのDSPy - 言語モデルを『プロンプト』ではなく『プログラミング』するための仕組み
masahiro_nishimi
2
500
AIと人間の共創開発!OSSで試行錯誤した開発スタイル
mae616
1
430
Domain-centric? Why Hexagonal, Onion, and Clean Architecture Are Answers to the Wrong Question
olivergierke
2
880
Range on Rails ―「多重範囲型」という新たな選択肢が、複雑ロジックを劇的にシンプルにしたワケ
rizap_tech
0
6.6k
Featured
See All Featured
Designing Experiences People Love
moore
142
24k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
55
3k
Java REST API Framework Comparison - PWX 2021
mraible
34
8.9k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
16
1.7k
Automating Front-end Workflow
addyosmani
1371
200k
Optimizing for Happiness
mojombo
379
70k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
45
2.5k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
127
53k
Leading Effective Engineering Teams in the AI Era
addyosmani
6
440
Build your cross-platform service in a week with App Engine
jlugia
232
18k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
140
34k
Transcript
Artificial Intelligence
Companies doing AI
[the AI revolution is] no longer a matter of if,
but when. — Tech Crunch 1 1 https://techcrunch.com/2016/07/18/why-the-top-5-tech-companies-are-dead-set-on-ai/
Neural networks
None
Neural networks on your phone
Snapchat Forevery Prisma
None
https://intune.com
None
BrainCore https://github.com/aleph7/BrainCore
InfiniteMonkeys https://github.com/craigomac/InfiniteMonkeys
None
Training a network Keras: https://github.com/fchollet/keras 2 2 https://github.com/fchollet/keras/blob/master/examples/lstm_text_generation.py
func loadNetFromFile(path: String) -> Net { guard let file =
File.open(path, mode: .ReadOnly) else { fatalError("File not found '\(path)'") } let lstm_1 = try! loadLSTMLayerFromFile(file, name: "lstm_1") let lstm_2 = try! loadLSTMLayerFromFile(file, name: "lstm_2") let denseLayer = loadDenseLayerFromFile(file) return Net.build { self.dataLayer => lstm_1 => lstm_2 => denseLayer => self.sinkLayer } }
let evaluator = try Evaluator(net: net, device: self.device) // Run
while running { evaluator.evaluate { snapshot in let char = sinkOutput() display(string: char) dataLayer.data = self.inputFromChar(char).elements } }
Alejandro Isaza https://github.com/aleph7