Apple Machine Learning Journal

  • However, to achieve high accuracy, the training sets need to be large, diverse, and accurately annotated, which is costly.
  • An alternative to labelling huge amounts of data is to use synthetic images from a simulator.
  • This is cheap as there is no labeling cost, but the synthetic images may not be realistic enough, resulting in poor generalization on real test images.
  • We show that training models on these refined images leads to significant improvements in accuracy on various machine learning tasks.
  • Read the article View the article “Improving the Realism of Synthetic Images”

Most successful examples of neural nets today are trained with supervision. However, to achieve high accuracy, the training sets need to be large, diverse, and accurately annotated, which is costly. An alternative to labelling huge amounts of data is to use synthetic images from a simulator. This is cheap as there is no labeling cost, but the synthetic images may not be realistic enough, resulting in poor generalization on real test images. To help close this performance gap, we’ve developed a method for refining synthetic images to make them look more realistic. We show that training models on these refined images leads to significant improvements in accuracy on various machine learning tasks.
Continue reading “Apple Machine Learning Journal”

Semiconductor Engineering .:. A Learning Machine For Machine Learning -Semiconductor Engineering

A Learning Machine For #MachineLearning --  #ArtificialIntelligence #AI

  • Many of these systems will need to work in real time, and that requires massive local processing capability.
  • Many options, but only one chance to pick the right combination to hit the power, performance and area (PPA) target of the final system.
  • To begin, you need a massive knowledge base of all combinations of process technologies, technology options, IP and package configurations.
  • You also need to capture the profiles of CPU, disk, memory and I/O bandwidth required for many types of advanced designs, and for the various steps in the design process.
  • A system that designs machine learning systems is still on the horizon, but using machine learning to help build machine learning chips is very real.

Building the systems that power machine learning is an immensely complex task.
Continue reading “Semiconductor Engineering .:. A Learning Machine For Machine Learning -Semiconductor Engineering”

Updated AWS Deep Learning AMIs with Apache MXNet 0.10 and TensorFlow 1.1 Now Available

Updated AWS Deep Learning AMIs with Apache MXNet 0.10 & TensorFlow 1.1 now available!

  • You can now use Apache MXNet v0.10 and TensorFlow v1.1 with the AWS Deep Learning AMIs for Amazon Linux and Ubuntu.
  • Apache MXNet announced version 0.10, available at http://mxnet.io, with significant improvements to documentation and tutorials including updated installation guides for running MXNet on various operating systems and environments, such as NVIDIA’s Jetson TX2.
  • Python PIP install packages are now available for the v0.10 release, making it easy to install MXNet on Mac OSX or Linux CPU or GPU environments.
  • Visit the AWS Marketplace to get started with the AWS Deep Learning AMI v1.4_Jun2017 for Ubuntu and the AWS Deep Learning AMI v2.2_Jun2017 for Amazon Linux.
  • The AWS Deep Learning AMIs are available in the following public AWS regions: US East (N. Virginia), US West (Oregon), and EU (Ireland).

You can now use Apache MXNet v0.10 and TensorFlow v1.1 with the AWS Deep Learning AMIs for Amazon Linux and Ubuntu. Apache MXNet announced version 0.10, available at http://mxnet.io, with significant improvements to documentation and tutorials including updated installation guides for running MXNet on various operating systems and environments, such as NVIDIA’s Jetson TX2. In addition, current tutorials have been augmented with definitions for basic concepts around foundational development components. API documentation is now more comprehensive, with accompanying samples. Python PIP install packages are now available for the v0.10 release, making it easy to install MXNet on Mac OSX or Linux CPU or GPU environments. These packages also include Intel’s Math Kernel Library (MKL) support for acceleration of math routines on Intel CPUs.
Continue reading “Updated AWS Deep Learning AMIs with Apache MXNet 0.10 and TensorFlow 1.1 Now Available”

Artificial Intelligence System Predicts Human Interactions – News Center

Hug or handshake? @MIT researchers created an #AI system that can predict human interactions

  • “I’m excited to see how much better the algorithms get if we can feed them a lifetime’s worth of videos,” says Vondrick. “
  • When predicting which of the four actions the person would perform one second later, the algorithm correctly predicted the action more than 43 percent of the time – and humans who have been watching TV for years were only able to predict the next action with 71 percent accuracy.
  • In their second study, the algorithm was shown frames from a video and asked it to predict what object will appear five seconds later.
  • Using a Tesla K40 GPU with the cuDNN -accelerated Caffe deep learning framework, the researchers trained their network on 600 hours of prime-time television shows including The Office and Desperate Housewives .
  • Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory developed an algorithm that can predict whether two individuals will hug, kiss, shake hands or slap five in the next scene.

Read the full article, click here.


@GPUComputing: “Hug or handshake? @MIT researchers created an #AI system that can predict human interactions”


Predicting what will happen in the future is challenging. Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory developed an algorithm that can predict whether two individuals will hug, kiss, shake hands or slap five in the next scene.


Artificial Intelligence System Predicts Human Interactions – News Center

Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification

End-to-end #MachineLearning: Automatic Image Colorization with Classification  #DataScience

  • Based on Convolutional Neural Networks, our deep network features a fusion layer that allows us to elegantly merge local information dependent on small image patches with global priors computed using the entire image.
  • We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features.
  • The entire framework, including the global and local priors as well as the colorization model, is trained in an end-to-end fashion.
  • The output of our model is the chrominance of the image which is fused with the luminance to form the output image.
  • Our architecture can process images of any resolution, unlike most existing approaches based on CNN. We leverage an existing large-scale scene classification database to train our model, exploiting the class labels of the dataset to more efficiently and discriminatively learn the global priors.

Read the full article, click here.


@MikeTamir: “End-to-end #MachineLearning: Automatic Image Colorization with Classification #DataScience”


We present a novel technique to automatically colorize
grayscale images that combines both global priors and local
image features. Based on Convolutional Neural Networks, our
deep network features a fusion layer that allows us to
elegantly merge local information dependent on small image
patches with global priors computed using the entire image. The
entire framework, including the global and local priors as well
as the colorization model, is trained in an end-to-end fashion.
Furthermore, our architecture can process images of any
resolution, unlike most existing approaches based on CNN. We
leverage an existing large-scale scene classification database
to train our model, exploiting the class labels of the dataset
to more efficiently and discriminatively learn the global
priors. We validate our approach with a user study and compare
against the state of the art, where we show significant
improvements. Furthermore, we demonstrate our method
extensively on many different types of images, including
black-and-white photography from over a hundred years ago, and
show realistic colorizations.


Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification