Building Convolutional Neural Networks with Tensorflow

Building Convolutional Neural Networks with #Tensorflow #abdsc

  • In the past year I have also worked with Deep Learning techniques, and I would like to share with you how to make and train a Convolutional Neural Network from scratch, using tensorflow.
  • Later on we can use this knowledge as a building block to make interesting Deep Learning applications.
  • Source code is also provided.
  • Before you continue, make sure you understand how a convolutional neural network works.
  • The code is also available in my GitHub repository, so feel free to use it on your own dataset(s).

In the past year I have also worked with Deep Learning techniques, and I would like to share with you how to make and train a Convolutional Neural Network from…
Continue reading “Building Convolutional Neural Networks with Tensorflow”

New neural-network algorithm learns directly from human instructions instead of examples

New neural-network algorithm learns directly from human instructions instead of examples  #ai

  • News New neural-network algorithm learns directly from human instructions instead of examples
  • For example, you could train a neural network to identify sky in a photograph by showing it hundreds of pictures with the sky labeled.
  • Abstract of Hair Segmentation Using Heuristically-Trained Neural Networks
  • Humans conventionally “teach” neural networks by providing a set of labeled data and asking the neural network to make decisions based on the samples it’s seen.
  • Applying the method to the binary classification of hair versus nonhair patches, we obtain a 2.2% performance increase using the heuristically trained NN over the current state-of-the-art hair segmentation method.

Conventional neural-network image-recognition algorithm trained to recognize human hair (left), compared to the more precise heuristically trained algorithm
Continue reading “New neural-network algorithm learns directly from human instructions instead of examples”

SERIOUS WONDER

Join the Fun and Play with Google's #AI Projects - SERIOUS WONDER

  • The Future of Propaganda is Audio and Facial Hacking November 15, 2016
  • B.J. Murphy is the Editor and Social Media Manager of Serious Wonder.
  • For years Google has been somewhat secretive over their projects dealing with Artificial Intelligence (AI).
  • “With all the exciting A.I. stuff happening, there are lots of people eager to start tinkering with machine learning technology.
  • Several company acquisitions and massive funding efforts later, Google is now prepared to reveal some of their projects to the world.

After several company acquisitions and massive funding efforts, Google is ready to show off their A.I. experiments! – B.J. Murphy for Serious Wonder
Continue reading “SERIOUS WONDER”

A.I. Experiments

  • Chrome Experiments Android Experiments Arts & Culture Experiments
  • Introducing A.I. Experiments.
  • Explore machine learning by playing with pictures, language, music, code, and more.
  • Giorgio Cam
  • Quick, Draw!

AI Experiments is a showcase for simple experiments that let anyone play with artificial intelligence and machine learning in hands-on ways, through pictures, drawings, language, music, and more.
Continue reading “A.I. Experiments”

These Are What the Google Artificial Intelligence’s Dreams Look Like

These Are What the Google Artificial Intelligence’s Dreams Look Like

  • Google continues to use these techniques to find out what their artificial neural networks are learning, and even ponders if it could shed light on the “roots of the creative process in general.”
  • Arms were often found in pictures of dumbbells, so the computer thought that sometimes dumbbells had arms.
  • The produce of an artificial neural network being asked to amplify and pull patterns out of white noise.
  • Google’s artificial neural networks (ANNs) are stacked layers of artificial neurons (run on computers) used to process Google Images.
  • Google used the ANN to amplify patterns it saw in pictures.

Spoiler alert: they’re as weird as electric sheep
Continue reading “These Are What the Google Artificial Intelligence’s Dreams Look Like”

Twitter has bought a machine learning startup that can sharpen real-time video

Twitter has bought a machine learning startup that can sharpen real-time video

  • Twitter has bought a machine learning startup that can automatically sharpen low-resolution and blurred video in real time.
  • Before (left) and after (right) Magic Pony’s algorithms have sharpened a video.
  • Magic Pony can improve pictures taken on low-res cameras
  • Giant floating art lets people walk on water across an Italian lake
  • Mark Zuckerberg fan art is the purest form of fan art on the web

Read the full article, click here.


@verge: “Twitter has bought a machine learning startup that can sharpen real-time video”


Twitter has bought a machine learning startup that can automatically sharpen low-resolution and blurred video in real time. The social network announced this morning that it had acquired…


Twitter has bought a machine learning startup that can sharpen real-time video

Google wants to find the art in artificial intelligence (Wired UK)

Google wants to find the art in artificial intelligence

  • In a talk at Moogfest, a US technology festival, Google researcher Douglas Eck described a project that would seek to understand whether or not a computer can create art.
  • Google wants to find the art in artificial intelligence
  • Google is launching a new project to see whether artificial intelligence can create art.
  • The project will initially attempt to create music, before moving onto images and then video
  • Eck hopes the openness of the project will encourage others to improve on the system.

Read the full article, click here.


@WiredUK: “Google wants to find the art in artificial intelligence”


Google is launching a new project to see if artificial intelligence can create art, music and videos


Google wants to find the art in artificial intelligence (Wired UK)