Skip to main content

Why Core ML will not work for your app (most likely)

While the buzz around newly released Apple framework is loud, I want to explain several things, that may not be obvious for those who are new to machine learning (ML).
  1. Core ML is not a machine learning framework.
  2. Core ML supports only two types of ML.
  3. If your models are proprietary or contain sensitive information, you can’t use CoreML.
  4. Core ML doesn’t solve the privacy concerns.
  5. Core ML doesn’t compress models.
  6. Core ML is not the only way to do machine learning on iOS.

Learn Machine Learning, not Core ML.
Impervious Invisibility

Google’s AutoML lets you train custom machine learning models without having to code
TechCrunch

Comments

Most Favorite Posts

j2obc - A Java to iOS Objective-C translation tool and runtime

What J2ObjC Is J2ObjC is an open-source command-line tool from Google that translates Java code to Objective-C for the iOS (iPhone/iPad) platform. This tool enables Java code to be part of an iOS application's build, as no editing of the generated files is necessary. The goal is to write an app's non-UI code (such as data access, or application logic) in Java, which is then shared by web apps (using GWT), Android apps, and iOS apps. J2ObjC supports most Java language and runtime features required by client-side application developers, including exceptions, inner and anonymous classes, generic types, threads and reflection. JUnit test translation and execution is also supported. J2ObjC is currently between alpha and beta quality. Several Google projects rely on it, but when new projects first start working with it, they usually find new bugs to be fixed. Apparently every Java developer has a slightly different way of using Java, and the tool hasn't translated all possib...

Google Drive versus Dropbox

MacWorld: Online Storage Face-Off: Google Drive vs. Dropbox

Server-driven UI (SDUI): Meet Zalandos AppCraft and AirBnB Lona

A short WTF: Joe Birch:  SERVER DRIVEN UI, PART 1: THE CONCEPT Zalando seems to follow the SDUI principle as well - defining a common design language and construct the screens on the backend while displaying them natively on the clients. They even go one step further; they implemented a mighty toolset to enable non-technical stakeholders to define their own native app screens Compass: Web tooling to create screens and bind data Beetroot: Backend service that combines the screen layout definition with the data Lapis/Golem: iOS/Android UI render engines Crazy cool! Good job, guys (when you do an open-source release?) To even move faster a Flutter based UI render engine implementation was great! See also AirBnB Lona SDUI approach Building a Visual Language Why Dropbox sunsetted its universal C++ mobile project and AirBnB its React Native implementation

PlistBuddy

If you want to generate a Plist within the shell script: The PlistBuddy command is used to read and modify values inside of a plist. Unless specified by the -c switch, PlistBuddy runs in interactive mode. Apple PlistBuddy ManPage

Why The Microsoft Surface Just Died Last Week

That was when the company’s new CEO, Satya Nadella, announced the launch of Office for the iPad. He emphasized the company’s focus on cloud and mobile for the future. “We think about users both as individuals and organizations spanning across all devices,” Nadella said during the launch event. And what he said effectively killed the Microsoft Surface. Forbes.com

CFPropertyList

The PHP implementation of Apple's PropertyList plist can handle XML PropertyLists as well as binary PropertyLists. It offers functionality to easily convert data between worlds, e.g. recalculating timestamps from unix epoch to apple epoch and vice versa. A feature to automagically create (guess) the plist structure from a normal PHP data structure will help you dump your data to plist in no time. github

App Indexing

A better search experience for apps and users with linking to in-app content. Google is working with app developers and webmasters to index the content of apps and relate them to websites. When relevant, Google Search results on Android will include deep links to apps. App Indexing