Vertex.AI

#PlaidML now has preliminary support for for Mac and Python 3:

#Keras #OpenCL #DeepLearning

  • Last week we announced the release of PlaidML, an open source software framework designed to enable deep learning on every device.
  • We received immediate requests for Mac and Python 3, today we’re pleased to announce preliminary support for both.
  • Installing PlaidML with Keras on a Mac is as simple as , but we’ve added something extra: – – We’ve updated plaidvision with support for macOS and Mac built-in webcams.
  • The actual installation only takes a moment: – – PlaidML on Mac is a preview and we are very interested in hearing about user experiences.
  • We’d especially like to thank GitHub user Juanlu001, our first open source contributor, for taking the lead on Python 3 support.

Last week we announced the release of PlaidML, an open source software framework designed to enable deep learning on every device. Our goal with PlaidML is to make deep learning accessible by supporting the most popular hardware and software already in the hands of developers, researchers, and students. Last week’s release supported Python 2.7 on Linux. We received immediate requests for Mac and Python 3, today we’re pleased to announce preliminary support for both.
Continue reading “Vertex.AI”

The Good, Bad, & Ugly of TensorFlow

The Good, Bad, and Ugly of #TensorFlow. #BigData #DeepLearning #MachineLearning  #AI

  • If you are deploying a model to a cloud environment, you want to know that your model can execute on the hardware available to it, without unpredictable interactions with other code that may access the same hardware.
  • For example, the Udacity tutorials and the RNN tutorial using Penn TreeBank data to build a language model are very illustrative, thanks to their simplicity.
  • For me, holding mental context for a new framework and model I’m building to solve a hard problem is already pretty taxing, so it can be really helpful to inspect a totally different representation of a model; the TensorBoard graph visualization is great for this.
  • But good programmers know it is much harder to write code that humans will use, versus code that a machine can compile and execute.
  • We appreciate their strategy of integrating new features and tests first so early adopters can try things before they are documented.

A survey of six months rapid evolution (+ tips/hacks and code to fix the ugly stuff) from Dan Kuster, one of indico’s deep learning researchers.
Continue reading “The Good, Bad, & Ugly of TensorFlow”

Become Michael Knight with Dashbot, an AI for your car

Become Michael Knight with Dashbot, an #AI for your car

  • CNN buys Casey Neistat’s Beme app, brings the YouTuber in-house
  • Sphero’s BB-8 wearable brings Force control to home automation with IFTTT support
  • The Das Keyboard Prime 13 brings the gaming keyboard to the board room
  • Uber’s China app is now separate from its global app – and a nightmare for foreigners
  • Insta360 Air looks to bring affordable 360 video to Android phones

Who needs a smart car when you have a cool car? The Dashbot is a $49 add on for your vehicle that allows you to interact with your phone and Alexa while..
Continue reading “Become Michael Knight with Dashbot, an AI for your car”

Bain Capital Ventures raises $600M fund with focus on SaaS, machine learning, more

Bain Capital Ventures closes new $600M fund with focus on SaaS, machine learning, more

  • Tags: Bain Capital Ventures , funding daily , investment fund
  • Bain Capital Ventures announced today in a public filing  that it has closed a $600 million investment fund.
  • Bain Capital Ventures raises $600M fund with focus on SaaS, machine learning, more
  • “We will also continue to balance investments geographically, including California which now represents half of our senior investment team and half of our investment dollars,â said Agarwal.
  • BCV managing director Ajay Agarwal tells VentureBeat that specific areas of focus for the new fund include “SaaS, machine learning, financial and retail technology, cybersecurity, cloud infrastructure and open source.”

Read the full article, click here.


@VentureBeat: “Bain Capital Ventures closes new $600M fund with focus on SaaS, machine learning, more”


Bain Capital Ventures announced today in a public filing that it has closed a $600 million investment fund.


Bain Capital Ventures raises $600M fund with focus on SaaS, machine learning, more

Regularization in Logistic Regression: Better Fit and Better Generalization?

Regularization in Logistic Regression: Better Fit & Generalization?  #MachineLearning @rasbt

  • Our new problem is to minimize the cost function given this added constraint.
  • We don’t want the model to memorize the training dataset, we want a model that generalizes well to new, unseen data.
  • In more specific terms, we can think of regularization as adding (or increasing the) bias if our model suffers from (high) variance (i.e., it overfits the training data).
  • A discussion on regularization in logistic regression, and how its usage plays into better model fit and generalization.
  • If we regularize the cost function (e.g., via L2 regularization), we add an additional to our cost function (J) that increases as the value of your parameter weights (w) increase; keep in mind that the regularization we add a new hyperparameter, lambda, to control the regularization strength.

Read the full article, click here.


@kdnuggets: “Regularization in Logistic Regression: Better Fit & Generalization? #MachineLearning @rasbt”


A discussion on regularization in logistic regression, and how its usage plays into better model fit and generalization.


Regularization in Logistic Regression: Better Fit and Better Generalization?

Magenta

Check out Magenta, an open-source ML research project looking at music and art generation -

  • If you’d like to keep up on Magenta as it grows, you can follow us on our GitHub and join our discussion group .
  • Soon we’ll begin accepting code contributions from the community at large.
  • We’ll use TensorFlow , and we’ll release our models and tools in open source on our GitHub.
  • We’re happy to announce Magenta, a project from the Google Brain team that asks: Can we use machine learning to create compelling art and music?
  • We’ll also post demos, tutorial blog postings and technical papers.

Read the full article, click here.


@googleresearch: “Check out Magenta, an open-source ML research project looking at music and art generation -”


Magenta is a project devoted to music and art generation with machine intelligence. It is part of TensorFlow, an open source machine learning library.


Magenta