Tensorflow -How to use Tensorboard tutorial

A brief and concise tutorial on how to visualize different aspects such as the loss of your neural network using tensorboard.

We are going to work with a fully-connected neural network using the MNIST dataset. I’m going to use the network I have introduced in an earlier post. It achieves on the test-set an accuracy of ~90%. This is not bad but we have no clue what is actually going on or how our model looks like. In this post we will add the necessary commands to visualize the graph and some training values using tensorboard. If you haven’t installed tensorflow yet look at this post. You also want to have a look at the official tensorflow documentation.

Write a Log File and Run Tensorboard
Tensorflow summaries are essentially logs. And in order to write logs we need a log writer (or what it is called in tensorflow) a SummaryWriter. So for starters,

Original URL: http://feedproxy.google.com/~r/feedsapi/BwPx/~3/bClt3ouPCa4/

Original article

Should your startup take the B Corp route?

 While most founders want to make a boatload of money, achieving a stunning exit is not the only driver for most entrepreneurs. Many are fueled by the challenge of solving a problem or producing something meaningful. Some want to make a corporate commitment to social responsibility by organizing their business as a B Corporation, with a mission to do good written into the governing documents. Read More

Original URL: http://feedproxy.google.com/~r/Techcrunch/~3/x616vxazPmY/

Original article

Learning Reinforcement Learning (with Code, Exercises and Solutions)

Skip all the talk and go directly to the Github Repo with code and exercises.
Why Study Reinforcement Learning
Reinforcement Learning is one of the fields I’m most excited about. Over the past few years amazing results like learning to play Atari Games from raw pixels and Mastering the Game of Go have gotten a lot of attention, but RL is also widely used in Robotics, Image Processing and Natural Language Processing.
Combining Reinforcement Learning and Deep Learning techniques works extremely well. Both fields heavily influence each other. On the Reinforcement Learning side Deep Neural Networks are used as function approximators to learn good representations, e.g. to process Atari game images or to understand the board state of Go. In the other direction, RL techniques are making their way into supervised problems usually tackled by Deep Learning. For example, RL techniques are used to implement attention mechanisms in image processing, or to optimize

Original URL: http://feedproxy.google.com/~r/feedsapi/BwPx/~3/xBYbtZddf54/

Original article

Why kernel development still uses email

Welcome to LWN.net

The following subscription-only content has been made available to you
by an LWN subscriber. Thousands of subscribers depend on LWN for the
best news from the Linux and free software communities. If you enjoy this
article, please consider accepting the trial offer on the right. Thank you
for visiting LWN.net!

Free trial subscription

Try LWN for free for 1 month: no payment
or credit card required. Activate
your trial subscription now and see why thousands of
readers subscribe to LWN.net.

In a world full of fancy development tools and sites, the kernel project’s
dependence on email and mailing lists can seem quaintly dated, if not
positively prehistoric. But, as Greg Kroah-Hartman pointed out in a Kernel
Recipes talk titled “Patches carved into stone tablets”, there are some
good reasons for the kernel community’s choices. Rather than being a
holdover from an older era, email remains the best way to manage a project
as large

Original URL: http://feedproxy.google.com/~r/feedsapi/BwPx/~3/VsFhJzsiNpU/

Original article

New Asterisk 14.0.1 now ships with Opus codec for high-quality audio

The past two years, we’ve heard from users about how great it’d be to officially integrate the Opus codec with Asterisk. Opus is the codec that’s used by millions of web browsers for WebRTC calls. It’s also known because it’s in a handful of VoIP phones, including Digium’s new D6x IP phones. Opus is better than a lot of other codecs because it provides great quality audio, even under very poor network conditions.
Until now, we’ve held off providing anything for Opus in Asterisk because of concerns about some intellectual property disclosures made against the codec. But today, we’re happy to announce that we’ve been able to resolve our concerns. So, along with Monday’s release of Asterisk 14.0, today, we’re putting out a new version, 14.0.1, that can finally and officially support Opus.
That’s the great news. The “sort of okay” news is that in order to resolve the legal concerns, we

Original URL: http://feedproxy.google.com/~r/feedsapi/BwPx/~3/3Lo2qADJ8J8/

Original article

The Berkeley Document Summarizer: Learning-Based, Single-Document Summarization


The Berkeley Document Summarizer is a learning-based single-document
summarization system. It compresses source document text based on constraints
from constituency parses and RST discourse parses. Moreover, it can improve
summary clarity by reexpressing pronouns whose antecedents would otherwise be
deleted or unclear.


The Berkeley Document Summarizer is described in:

“Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints”
Greg Durrett, Taylor Berg-Kirkpatrick, and Dan Klein. ACL 2016.

See http://www.eecs.berkeley.edu/~gdurrett/ for papers and BibTeX.

Questions? Bugs? Email me at gdurrett@eecs.berkeley.edu


Copyright (c) 2013-2016 Greg Durrett. All Rights Reserved.

This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
GNU General Public License for more

Original URL: http://feedproxy.google.com/~r/feedsapi/BwPx/~3/ynaD3ZMggOg/berkeley-doc-summarizer

Original article

Ask Slashdot: Should An Open Source Hardware Project Support Clones?

Long-time Slashdot reader Ichijo
has a question about “(not quite) open source hardware”:
One hardware project that calls itself “open source” doesn’t want to make its hardware design source files publicly available because doing so would, in their words, “make it very trivial for e.g Chinese companies to start producing cheap clones… we’d be getting support requests for hardware we had no idea of the quality of.” This answer was in response to a request by a user who wants to use the design in his own projects.

Have any other open source hardware projects run into support issues from people owning cheap “clones”? Have clones been produced even without the hardware design source files?

Leave your answers in the comments. Should an open source hardware project support clones?

Read more of this story at Slashdot.

Original URL: http://rss.slashdot.org/~r/Slashdot/slashdot/~3/FRMLzvS4TgA/ask-slashdot-should-an-open-source-hardware-project-support-clones

Original article

Proudly powered by WordPress | Theme: Baskerville 2 by Anders Noren.

Up ↑

%d bloggers like this: