Siraj Raval explores the use of AI in classifying diseases in medical imagining.
Here’s an interesting interview with Josh Dillon, who works on Tensorflow.
In this video, he discusses working on the Distribution API, which is based on probabilistic programming. Watch this video to find out what exactly probabilistic programming is, where the use of Distributions and Bijectors comes into play, & how you can get started. Subscribe to our channel to stay up to date with Google Developers.
This week James Montemagno is joined by Jim Bennett, a Cloud Developer Advocate at Microsoft, who shows us how to use AI inside a mobile app to identify his daughters’ toys.
In the video below, he walks through using the Azure custom vision service to generate a model to identify different toys, then shows how you can use these models from inside your app, both remotely by calling an Azure service, or locally by running the model on your device using CoreML and Tensorflow.
- Azure Custom Vision service
- Custom Vision service docs
- Sample toy identifier app
- Xamarin plugin to use CoreML and Tensorflow with custom vision models
- Find James on: Twitter, GitHub, Blog, and his weekly development podcast Merge Conflict.
- Follow @JamesMontemagno
- Never Miss an Episode: Follow @TheXamarinShow
- Find Jim on: Twitter, GitHub, Blog, Jim’s book – Xamarin In Action
TensorFlow is a powerful data flow-oriented machine learning framework developed by Google’s Brain Team. It was designed to be easy to use and widely applicable on both numeric, neural network-oriented problems as well as other domains.
Here’s a video from Google introducing the techniques you can use to represent features – including Bucketing, Crossing, Hashing, and Embedding – and other utilities TensorFlow uses to help you create features.
The video is worth a watch just for the walkthrough of using TensorFlow Estimators to classify structured data.
Tensorflow, Google’s framework for machine learning and neural networks , has recently been open-sourced.
With this new tool, deep machine learning transitions from an area of research into the mainstream of software engineering.
In this session, Martin Görner teaches you how to pick the correct neural network type for your problem and how to make it behave.
A PhD or familiarity with differential equations is no longer required.