Venturebeat - Machine Learning

ExtremeTech - Machine Learning

Nuit Blanche

  • !Compressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networks
    Reconstruction solvers requiring too muh time to recontruct images or videos is nothing new as pointed out four years ago ( Sunday Morning Insight: Faster Than a Blink of an Eye). Last week, we saw another example of that in DiffuserCam: Lensless Sin…
    - 15 hours ago 17 Oct 17, 5:00am -
  • PhD Thesis: Efficient Methods and Hardware for Deep Learning by Song Han
    Congratulations Dr. Han !The thesis is listed below but many of themes are part of lecture 15 of Stanford CS 231n's Convolutional Neural Networks for Visual Recognition (Spring 2017 ). Enjoy !Efficient Methods and Hardware for Deep Learning by Son…
    - 5 days ago 12 Oct 17, 3:30pm -
  • Slides and Videos: Deep RL Bootcamp 26-27 August 2017, Berkeley CA
    Thanks to Pieter's twitter stream, I just noticed the slides and videos of the Deep RL Bootcamp that took place on 26-27 August 2017 at Berkeley. Enjoy :LecturesCore Lecture 1 Intro to MDPs and Exact Solution Methods -- Pieter Abbeel (video | slides)…
    - 6 days ago 11 Oct 17, 9:14pm -
  • DiffuserCam: Lensless Single-exposure 3D Imaging
    One word: Awesome !DiffuserCam: Lensless Single-exposure 3D Imaging by Nick Antipa, Grace Kuo, Reinhard Heckel, Ben Mildenhall, Emrah Bostan, Ren Ng, Laura WallerWe demonstrate a compact and easy-to-build computational camera for single-shot 3D imag…
    - 8 days ago 10 Oct 17, 6:16am -
  • Slides: Université Cote d'Azur/UCA Deep Learning School, May 2017
    At the recent France is AI event, Stephane mentioned to me that a Deep Learning School had been organized by (another) Stéphane and Frédéric this past June in Nice. Here are the slides:Panorama du Deep Learning aujourd'hui : Stéphane Canu (Deep…
    - 10 days ago 7 Oct 17, 3:28pm -

Microsoft - Machine Learning

  • The Microsoft Team Data Science Process (TDSP) – Recent Updates
    This post is authored by Xibin Gao, Data Scientist, Wei Guo, Data Scientist, Brad Severtson, Senior Content Developer, and Debraj GuhaThakurta, Senior Data Scientist Lead, at Microsoft What is TDSP Improving the efficiency of developing and deploying…
    - 8 days ago 9 Oct 17, 4:00pm -
  • How Stack Overflow Can Use Microsoft AI to Empower Every Developer
    This post is authored by Anand Raman, Chief of Staff for the Cloud AI team at Microsoft. Artificial Intelligence has emerged as one of the most disruptive forces behind the digital transformation of business. Soon, most enterprises will depend on AI…
    - 22 days ago 25 Sep 17, 4:00pm -
  • Ignite 2017: Announcing Tools for AI-Driven Digital Transformation
    Re-posted from the Microsoft Azure blog. Artificial Intelligence (AI) has emerged as one of the most disruptive forces behind the digital transformation of business. Earlier today, at Microsoft Ignite 2017, where we are in conversations about digital…
    - 22 days ago 25 Sep 17, 2:08pm -
  • Using the Team Data Science Process (TDSP) in Azure Machine Learning
    This post is authored by Wei Guo, Data Scientist, Hai Ning, Principal PM Manager, Xibin Gao, Data Scientist, Brad Severtson, Senior Content Developer, and Debraj GuhaThakurta. Senior Data Scientist Lead, at Microsoft. In this post, we describe how th…
    - 22 days ago 25 Sep 17, 2:00pm -
  • Data Transformations “By Example” in the Azure Machine Learning Workbench
    This post is authored by Ranvijay Kumar, Senior Program Manager at Microsoft. In this post, I talk about the Derive Column By Example transformation – an unexpected, powerful and super-efficient way to perform complex data transformations in the Az…
    - 22 days ago 25 Sep 17, 2:00pm -

insideBIGDATA

  • !AtScale 6.0 Brings the Benefits of its Universal Semantic Layer to the Google Cloud
    AtScale, the company providing enterprises with a universal semantic platform for BI on Big Data, announced the general availability of AtScale 6.0. With this release, customers will see unparalleled cost savings when deploying analytical workloads…
    - 3 hours ago 17 Oct 17, 5:00pm -
  • !Book Review: Python Data Science Handbook
    I recently had a need for a Python language resource to supplement a series of courses on Deep Learning I was evaluating that depended on this widely used language. As a long-time data science practitioner, my language of choice has been R, so I reli…
    - 5 hours ago 17 Oct 17, 3:30pm -
  • Alation’s Enterprise Data Catalog Values Data Assets for the Chief Data Officer
    Alation Inc., the collaborative data company, announced increased support for Chief Data Officers looking to manage their data as an asset. Alation 5.0 will include new features and a services package to make data asset valuation simple by promoting…
    - 1 day ago 16 Oct 17, 5:00pm -
  • Why Hospitals Need Big Data to Improve Patient Experience
    In this special guest feature, Senem Guney, PhD, CPXP, Founder and Chief Experience Officer at NarrativeDx, discusses why hospitals need big data to improve patient experience. Hospital administrators seeking to provide excellent patient experiences…
    - 1 day ago 16 Oct 17, 3:30pm -
  • The Role of the Modern Data Scientist — And How Everyone Has the Power to Become One
    In this contributed article, Arijit Sengupta, Head of Einstein Discovery at Salesforce, explains - given the role of the modern data scientist, everyone has the power to become one. We aren't that far off from a future when everyone will have the too…
    - 1 day ago 16 Oct 17, 3:30pm -

The Conversation - Machine Learning

Daniel Lemire

  • The Harvey-Weinstein scientific model
    It is widely believed that science is the process by which experts collectively decide on the truth and post it up in “peer-reviewed journals”. At that point, once you have “peer-reviewed research articles” then the truth is known. Less naïv…
    - 4 days ago 14 Oct 17, 2:01am -
  • Science and Technology links (October 13th, 2017)
    Rodney Brooks, who commercialized robots that can vacuum your apartment, has written a great essay on artificial intelligence. It is worth reading. There is some concern that the computers necessary to control a self-driving car will use so much powe…
    - 4 days ago 13 Oct 17, 9:28pm -
  • Bee-level intelligence
    How close are we to having software that can emulate human intelligence? It is hard to tell. One problem with human beings is that we have large brains, with an almost uncountable number of synapses. We have about 86 billion neurons. This does not se…
    - 4 days ago 13 Oct 17, 5:36pm -
  • Post-Blade-Runner trauma: From Deep Learning to SQL and back
    Just after posting my review of the movie Blade Runner 2049, I went to attend the Montreal Deep Learning summit. Deep Learning is this “new” artificial-intelligence paradigm that has taken the software industry by storm. Everything, image recogni…
    - 6 days ago 11 Oct 17, 3:54pm -
  • On Blade Runner 2049
    Back in 1982, an incredible movie came out, Blade Runner. It told the story of “artificial human beings” (replicants) that could pass as human beings, but had to be hunted down. The movie was derived from a novel by Philip Dick. It took many year…
    - 8 days ago 9 Oct 17, 9:30pm -

Large Scale Machine Learning

  • Prof. Joseph Keshet from BIU fools deep learning
    My friend Joseph (Yossi) Keshet have recently released work for fooling deep learning systems. His work got a lot of attendion including MIT Technology Review and the New Scientist. Nice work!!
    - 39 days ago 8 Sep 17, 5:51pm -
  • Dataiku raised 28M$
    According to VentureBeat Dataiku just raised 28M$. Dataiku has a web based platform for data science.Here is my personal connection. Strangely last time I wed a couple I was wearing their t-shirt.Unrelated, I just learned from my colleague Brian that…
    - 39 days ago 8 Sep 17, 5:45pm -
  • Deepgram - Audio Search with Deep Learning
    A very interesting podcast by Sam Charrington who is interviewing Scott Stephenson from DeepGram. DeepGram is using deep learning activations for creating indexes that allows to search text in voice recordings.DeepGram have released Kur which is a hi…
    - 43 days ago 5 Sep 17, 4:19am -
  • Some misc news
    I just learned my postdoc roommate Yisong Yue from Caltech released a new interesting paper: Factorized Variational Autoencoders for Modeling Audience Reactions to Movies: a joint work with Disney Research, published @ CVPR 2017.Another interesting p…
    - 83 days ago 27 Jul 17, 6:07am -
  • Data Science Summit Europe 2017
    The 3rd Data Science Summit Europe is coming! This year I am not involved in the organization she it should probably be a better event :-) Save the date - May 29, 2017 in Jerusalem. The date was picked just after O'Reilly Strata London 2017 thus the…
    - 13 Feb 17, 7:06am -

Technet - Machine Learning

  • The Microsoft Team Data Science Process (TDSP) – Recent Updates
    This post is authored by Xibin Gao, Data Scientist, Wei Guo, Data Scientist, Brad Severtson, Senior Content Developer, and Debraj GuhaThakurta, Senior Data Scientist Lead, at Microsoft What is TDSP Improving the efficiency of developing and deploying…
    - 8 days ago 9 Oct 17, 4:00pm -
  • How Stack Overflow Can Use Microsoft AI to Empower Every Developer
    This post is authored by Anand Raman, Chief of Staff for the Cloud AI team at Microsoft. Artificial Intelligence has emerged as one of the most disruptive forces behind the digital transformation of business. Soon, most enterprises will depend on AI…
    - 22 days ago 25 Sep 17, 4:00pm -
  • Ignite 2017: Announcing Tools for AI-Driven Digital Transformation
    Re-posted from the Microsoft Azure blog. Artificial Intelligence (AI) has emerged as one of the most disruptive forces behind the digital transformation of business. Earlier today, at Microsoft Ignite 2017, where we are in conversations about digital…
    - 22 days ago 25 Sep 17, 2:08pm -
  • Using the Team Data Science Process (TDSP) in Azure Machine Learning
    This post is authored by Wei Guo, Data Scientist, Hai Ning, Principal PM Manager, Xibin Gao, Data Scientist, Brad Severtson, Senior Content Developer, and Debraj GuhaThakurta. Senior Data Scientist Lead, at Microsoft. In this post, we describe how th…
    - 22 days ago 25 Sep 17, 2:00pm -
  • Data Transformations “By Example” in the Azure Machine Learning Workbench
    This post is authored by Ranvijay Kumar, Senior Program Manager at Microsoft. In this post, I talk about the Derive Column By Example transformation – an unexpected, powerful and super-efficient way to perform complex data transformations in the Az…
    - 22 days ago 25 Sep 17, 2:00pm -

Machinalis

  • Blank check for Machine Learning investments?
    During our years of work dealing with problems in the industry around Machine Learning, we’ve observed that one of the key moments in a company is the one when it has to define where to invest. For other possible investments, decision makers have u…
    - 63 days ago 15 Aug 17, 2:16pm -
  • Presenting at the PyData London meetup
    Last week I had the chance to speak at the 32nd PyData London meetup. For those who haven't been there, the PyData London meetup community is the biggest one around (it recently went over 5000 members!). But it's not just big, it's always an opport…
    - 21 Mar 17, 1:39pm -
  • PyConAr 2016
    A few days ago (November 25, 26 and 27th) the 8th edition of PyCon Argentina took place in Bahía Blanca, a city 600km to the south of Buenos Aires, and I was lucky enough to be able to go with a group of other people from Machinalis.PyConAr is the…
    - 7 Dec 16, 8:02pm -
  • Watermarking images on Django sites
    Have you ever noticed how stock photography sites add watermarks to the images shown on their catalogs? They do that to make sure people don’t just take the free samples and use them without proper licensing. Google Maps does it for the satellite i…
    - 22 Nov 16, 2:54pm -
  • Integrating Pandas, Django REST Framework and Bokeh
    It’s no secret that we love Django REST Framework. We’ve written quite a few blog posts about it and it is our default framework for projects that require a web API.Another package that we use a lot is Pandas (and NumPy by extension). It is fast…
    - 25 Oct 16, 12:16pm -

Alex Woods - Machine Learning

  • Dijkstra’s Algorithm in Python
    Dijkstra’s algorithm is one of the key algorithms we hear about within computer science. It can be slightly less accessible to beginners because you have to know what a weighted, directed graph is.  The algorithm takes a starting node and outputs…
    - 2 Oct 16, 9:17pm -
  • Terminal
    Being able to navigate around your file system is a key skill, and it can really speed up your workflow. Here is a set of what I think are some really useful terminal commands and tips. Note – My terminal has the current directory right after the a…
    - 16 Sep 16, 8:28pm -
  • Counting is Hard
    Combinatorics and Probability—I love this kind of math. Here are some interesting problems I’ve gotten most of these from classes I’ve taken. Two of them (the triangle one and the combinatorial proof one) took me a few hours to solve, and each…
    - 10 Sep 16, 5:15pm -
  • Entropy
    Information theory sits comfortably in between electrical engineering and statistics / machine learning. It’s founding came from the 1948 masters thesis of Claude Shannon—arguably the most important masters thesis ever written. In “A Mathematic…
    - 10 Apr 16, 4:14pm -
  • Great Paper on AdaBoost
    In the past week, I really enjoyed this paper. It’s about boosting, which arose as a solution to the question—“Can a set of weak learners create a strong learner?” The solution is pretty fascinating. You basically pit a bunch of weak learners…
    - 10 Feb 16, 1:06am -

Machine Learning Mastery

  • !How to Clean Text for Machine Learning with Python
    You cannot go straight from raw text to fitting a machine learning or deep learning model. You must clean your text first, which means splitting it into words and handling punctuation and case. In fact, there is a whole suite of text preparation meth…
    - 2 hours ago 17 Oct 17, 6:00pm -
  • How to Develop an Encoder-Decoder Model with Attention for Sequence-to-Sequence Prediction in Keras
    The encoder-decoder architecture for recurrent neural networks is proving to be powerful on a host of sequence-to-sequence prediction problems in the field of natural language processing such as machine translation and caption generation. Attention i…
    - 1 day ago 16 Oct 17, 6:00pm -
  • How to Prepare Movie Review Data for Sentiment Analysis
    Text data preparation is different for each problem. Preparation starts with simple steps, like loading data, but quickly gets difficult with cleaning tasks that are very specific to the data you are working with. You need help as to where to begin a…
    - 2 days ago 15 Oct 17, 6:00pm -
  • How Does Attention Work in Encoder-Decoder Recurrent Neural Networks
    Attention is a mechanism that was developed to improve the performance of the Encoder-Decoder RNN on machine translation. In this tutorial, you will discover the attention mechanism for the Encoder-Decoder model. After completing this tutorial, you w…
    - 5 days ago 12 Oct 17, 6:00pm -
  • What Are Word Embeddings for Text?
    Word embeddings are a type of word representation that allows words with similar meaning to have a similar representation. They are a distributed representation for text that is perhaps one of the key breakthroughs for the impressive performance of d…
    - 7 days ago 10 Oct 17, 6:00pm -