This project now has a hackaday.io link: https://hackaday.io/project/12261-raspberry-pi-facebook-chatbot
If you haven’t heard already, Facebook recently announced their new Messenger based chatbot store at the F8 Facebook Developer conference in San Fransisco. Along with that, they also announced a platform called Wit.ai aimed at making it easy to give your bot natural language understanding. In this video series, I’m going to be making a Raspberry Pi powered Facebook Chatbot with the *new* Raspbery Pi 3. The chatbot will be coded to send me news articles on demand.
In this video, I finish my chatbot by integrating Wit.ai to give my bot a NLU (Natural Language Understanding) component.
EDIT: After shooting the video, I realized that I forgot to load the code on my raspberry pi. It should be the same as the other two videos though. Pull the code from github and run `npm start`.
If you have any suggestion for how to improve the chatbot, or how to improve these videos, please let me know it a comment below!
See my code on Github: https://github.com/HackerHouseYT/Facebook-Newsbot
Facebook chatbot platform: https://developers.facebook.com/blog/post/2016/04/12/bots-for-messenger/
Node.js on a Raspberry Pi: https://learn.adafruit.com/node-embedded-development/installing-node-dot-js
Subscribe to Hacker House: https://www.youtube.com/channel/UCEcNXmr7DYq1XxpWHSxaN0w?sub_confirmation=1
Follow Hacker House on Instagram:
The Sights by Mr. Logistix (buukwerm) is licensed under a Creative Commons Attribution license (http://creativecommons.org/licenses/by-sa/3.0/)
Facebook’s Caffe2 AI tools travel to iPhone, Android, as well as Raspberry Pi
Your smart phone may soon have the ability to recognise objects in images without the need of getting access to the cloud
New intelligence can be put into cellular devices for example, the iPhone, Android OS products, and low-power PCs such as Raspberry Pi with Facebook’s new open-source Caffe2 deep-learning framework.
Caffe2 enables you to program artificial intelligence features into tablets and smartphones, allowing them to recognize photos, movie, text, and speech and be more situationally aware.
It is critical to realize that Caffe2 isn’t an AI program, but a tool making it possible for AI to be programmed into mobile phones. It does take just a couple of lines of code to write learning models, which could then be bundled into mobile apps.
The launch of Caffe2 is important. It signifies people will be capable to get image recognition, natural language processing, and computer vision directly on their mobile phone. That job is often offloaded to remote servers in the cloud, with mobile phones then connecting to it.
Mobile devices are having more and more artificial intelligence abilities. More mobile phones are being bundled up with Amazon’s Alexa and Google Assistant, while Apple’s Siri has been a staple in the iPhone for many years. Samsung’s Galaxy S8 mobile phones are due to get the Bixby voice assistant, which should make operating the mobile phones incredibly easier.
Caffe2 can work within the power constraints of mobile devices. It works with mobile hardware to accelerate AI apps and create neural networks.
Caffe2 employs the computing power of latest mobile hardware to increase the speed of deep-learning jobs. One example is, in mobile phones, Caffe2 will utilize the computing power of Adreno GPUs and Hexagon DSPs on Qualcomm’s Snapdragon mobile chipsets.
Continue reading at http://pcworld.com/article/3190759/artificial-intelligence/facebooks-caffe2-ai-tools-come-to-iphone-android-and-raspberry-pi.html