쑤쑤_CS 기록장
Chapter 1, Machine Learning, iOS & You 본문
<챕터1과 그 시작>
Section I: Machine Learning with Images
section 1 에서는 machin learing with Images를 다룹니다.
이미지를 활용하여 ML을 진행하는 과정입니다.
이때
machine learning 의 경우 python을 이용해서 코드를 작성합니다.
우리의 목표는 "how to use machine learning techniques to solve problems using images"의 방법을 아는 것 입니다.
챕터1에서 공부한 내용의 목차는 아래와 같습니다.
코드 실습 없이 machine learning의 이론적인 부분을 다룹니다.
* What is machine learning?
* Learning without explicit programming
* Deep learning
* Artificial intelligence
* What can you do with machine learning?
* ML in a nutshell
* Supervised learning
* You need data.. a lot of it
* It's all about the features
* The training loop
* What does the model actually learn?
* Transfer learning : Just add data
* Can mobile devices really do machine learning?
* Why not in the cloud?
* Frameworks, tools and APIs
* Apple's task - specific frameworks
- Vision
_ Natural Language
_ SoundAnalysis
_ Speech
_ SiriKit
_ GameplayKit
* Core ML ready-to-use models
* Convert existing models with coremltools
_ Apache MXNet
_ Caffe
_ Keras
_ PyTorch
_ scikit-learn
_ TensorFlow
* Transfer learning with Create ML and TuriCreate
* Turi Create's statistical models
* Build your own model in Keras
* Gettin' jiggy with the algorithms
* Third-party frameworks
* ML all the things?
* The ethics of machine learning
* Biased data, biased model
* Exlainable/interpretable/transparent AI
* Key points
• Machine learning isn’t really that hard to learn — Stick with this book and you’ll see!
• Access to large amounts of data and computing power found online has made machine learning a viable technology.
• At its core, machine learning is all about models; creating them, training them, and inferring results using them.
• Training models can be an inexact science and an exercise in patience.
However, easy-to-use transfer learning tools like Create ML and Turi Create can help improve the experience in specific cases.
• Mobile devices are pretty good at inferring results.
With Core ML 3, models can be personalized using a limited form of on-device training.
• Don’t confuse machine learning with Artificial Intelligence.
Machine learning can be a great addition to your app, but knowing its limitations is equally important.
'IT 지식 기록 > ML for iOS | 인공지능' 카테고리의 다른 글
Xcode - 앱 이름 바꾸기 (0) | 2020.07.13 |
---|---|
Xcode - this target might include its own product 에러 (0) | 2020.07.13 |
Xcode - building could produce unreliable results 에러 (0) | 2020.07.13 |
Chapter2 : Getting Started with Image Classification (0) | 2020.07.13 |
Machine Learning by Tutorials v2.4.0 (0) | 2020.07.13 |