AI News Monday, March 12 Multiple object, Deep learning, Content & more…


AI News TLDR / Table of Contents

[/vc_column_text][/vc_column][/vc_row][vc_row el_id=”Mine-Your-Photos-and-Videos-on-Linode-Using-Deep-Learning-Face-Recognition”][vc_column width=”1/2″][vc_separator][vc_column_text]

Mine Your Photos and Videos on Linode Using Deep Learning & Face Recognition

[/vc_column_text][vc_column_text el_class=”topfeed-summary-list”]

  • Mine Your Photos and Videos on Linode Using Deep Learning Face RecognitionIn this article, I explore the Linode clouds capabilities at running challenging computer vision tasks like deep learning, multiple object detection and face recognition.
  • A multiple object detector is a component that uses deep learningspecifically, a pre-trained YOLO deep convolutional neural networkto identify objects and their locations in a photo or video.
  • Overview ofstepsSelect machines to run the software on.Install prerequisite software on those machines.Upload your photo collections to those machines.Optionally train the face recognition system.Start visual mining of your photo collections.Download the reports and other annotated outputs of the mining, and import them into a database or text search engine for…
  • This means the machine should have enough storage capacity not just for the photo collection you wish to mine but also for storing the pipelines configured outputs, possibly including text reports, annotated photos, annotated video frames and annotated videos (annotated video frames are especially heavy on storagefor example, a single…
  • The summary of steps are described here, while detailed commands and caveats are in Train the face recognizer section: – Go through your photo collections and select a subset of photos containing all the individuals whose faces you want the system to recognize.Facial areas of individuals should be cropped from…

[/vc_column_text][vc_column_text el_class=”topfeed-tags”]Tags: multiple object, deep learning, multiple object detection, face recognition, multiple object detector[/vc_column_text][/vc_column][vc_column width=”1/2″][vc_separator][vc_column_text el_class=”topfeed-tweet”]

[/vc_column_text][vc_column_text el_class=”topfeed-embedly”]Mine Your Photos and Videos on Linode Using Deep Learning & Face Recognition[/vc_column_text][/vc_column][/vc_row][vc_row el_id=”Three-Ways-to-Make-Content-Part-of-Your-Design-Strategy”][vc_column width=”1/2″][vc_separator][vc_column_text]

Three Ways to Make Content Part of Your Design Strategy

[/vc_column_text][vc_column_text el_class=”topfeed-summary-list”]

  • Three Ways to Make Content Part of Your DesignStrategyWritten by: Leigh Bryant – You know what they say: Its a content-driven world, and were all living in it.
  • At the audit stage, youll need to determine two things: what kinds of content there are (articles, videos, images, interactive modules, and so on) and how much of each of those will be featured in the future.
  • Probably, however, you dont. Unless theres a content expert on staff able to provide the resources to you, you want to, at minimum, get all of the content types established and at least a general sense of which ones are most important to the business.
  • But its also harder, because youll need to determine what kinds of content could be used, and in what ways youll be using them.
  • We cant claim to be creating anything like user-centred designs if were not thinking about the content the users interact with from the earliest stages of our work.

[/vc_column_text][vc_column_text el_class=”topfeed-tags”]Tags: content, design process, content management team, content consumer experience, content creation process[/vc_column_text][/vc_column][vc_column width=”1/2″][vc_separator][vc_column_text el_class=”topfeed-tweet”]

[/vc_column_text][vc_column_text el_class=”topfeed-embedly”]Three Ways to Make Content Part of Your Design Strategy[/vc_column_text][/vc_column][/vc_row][vc_row el_id=”A-Quick-Easy-Guide-to-Deep-Learning-with-Java—Deeplearaning4j-DL4J”][vc_column width=”1/2″][vc_separator][vc_column_text]

A Quick Easy Guide to Deep Learning with Java – Deeplearaning4j / DL4J

[/vc_column_text][vc_column_text el_class=”topfeed-summary-list”]

  • We are going to build our first simple neural network usingOpen-Source, Distributed, Deep Learning Library for the JVM Deeplearning4jor DL4J – – Machine Learning is taking over the web.
  • When you network model has more than 2 layers (including input and output layer), its considered as Deep Neural Net.
  • The data in a file is like: – – The last column is a classifier and the classification is: – – Deeplearning4j used DataVec libraries to read the data from the different sources and convert them to machine-readable format i.e. Numbers.
  • We will put together a simple utility function that accepts file path, batch size, label index and a number of classes.
  • We will define a simple class to map all those columnsin test data: – – Now lets write a simple utility method to get ourobjects.

[/vc_column_text][vc_column_text el_class=”topfeed-tags”]Tags: data, test data, Deep Learning, model, neural network[/vc_column_text][/vc_column][vc_column width=”1/2″][vc_separator][vc_column_text el_class=”topfeed-tweet”]

[/vc_column_text][vc_column_text el_class=”topfeed-embedly”]A Quick Easy Guide to Deep Learning with Java – Deeplearaning4j / DL4J – opencodez[/vc_column_text][/vc_column][/vc_row]