Sara Collins

183 Flips | 4 Magazines | 81 Likes | 14 Followers | @scollins050815 | Keep up with Sara Collins on Flipboard, a place to see the stories, photos, and updates that matter to you. Flipboard creates a personalized magazine full of everything, from world news to life’s great moments. Download Flipboard for free and search for “Sara Collins”

Pushpin — An Open Source Library That Turns REST APIs into Realtime APIs

An intro to evented APIs and how to build them with Pushpin<p>“Real-time” is becoming an omnipresent force in the modern tech stack. As consumers demand …

How to Prepare Univariate Time Series Data for Long Short-Term Memory Networks

It can be hard to prepare data when you’re just getting started with deep learning.Long Short-Term Memory, or LSTM, recurrent neural networks expect …

Introducing tf-seq2seq: An Open Source Sequence-to-Sequence Framework in TensorFlow

Posted by Anna Goldie and Denny Britz, Research Software Engineer and Google Brain Resident, Google Brain Team<i><br>(Crossposted on the Google Open Source</i> …

Artificial Neural Networks & It's Applications

Overview and Applications of Artificial Neural Networks<p>Reading Time: 17 Minutes<p>by Navdeep Singh Gill | May 05, 2017 | Categories - Artificial Neural …

Keras Cheat Sheet: Neural Networks in Python

Python For Data Science Cheat Sheet: Keras<p>Keras is a powerful and easy-to-use deep learning library for Theano and TensorFlow that provides a …

The "universal adversarial preturbation" undetectably alters images so AI can't recognize them

In a newly revised paper in <i>Computer Vision and Pattern Recognition</i>, a group of French and Swiss computer science researchers show that "a very small …

A data science team’s tips to the ‘path of less wrongness’

<i>The first principle is that you must not fool yourself, and you are the easiest person to fool. – Richard Feynman</i><p>Data scientists are having their day …

Parallel Python - Home

<b>Overview:</b><p><b>PP</b> is a python module which provides mechanism for parallel execution of python code on <b>SMP</b> (systems with multiple processors or cores) and</b> …

An experiment with awesome deep learning papers

There have been several lists of deep learning papers doing the rounds. Recently Terry Taewoong Um’s list of the top 100 awesome and most cited deep …

Deep Learning and Machine Learning Guide: Part III

Take a Course!<p>This link is a good start. There's lots of them.<p><b>Read a Book!</b><p>I can highly recommend <i>Deep Learning: A Practioner's Approach.</i> From a …

Composing Deep-Learning Microservices for the Hybrid Internet of Things

Deep learning is steadily remaking every aspect of our world. But it can’t achieve that potential unless developers have the right tools for …

Deep Voice: Baidu takes Google's amazing voice-making AI and makes it even faster, better

The Chinese search giant has built on DeepMind's Wavenet and created a version of the algorithm that can be trained in a matter of hours and perform …

Google is acquiring data science community Kaggle

Sources tell us that Google is acquiring Kaggle, a platform that hosts data science and machine learning competitions. Details about the transaction remain somewhat vague, but given that Google is hosting its Cloud Next conference in San Francisco this week, the official announcement could come as …

Facebook's new machine learning framework emphasizes efficiency over accuracy

In machine learning parlance, clustering or similarity search looks for affinities in sets of data that normally don't make such a job easy. If you …

Deep Learning Project Workflow

This document attempts to summarize Andrew Ng's recommended machine learning workflow from his "Nuts and Bolts of Applying Deep Learning" talk at …

Up to Speed on Deep Learning: February Update

Sharing some of the latest research, announcements, and resources on deep learning.<p><i>By Isaac Madan</i><p>Continuing our series of deep learning updates, we …

How to do Speech Recognition with Deep Learning

This post is by Adam Geitgey, Machine Learning Consultant Speech recognitionThe post How to do Speech Recognition with Deep Learning appeared first …

A gallery of interesting Jupyter Notebooks

This page is a curated collection of Jupyter/IPython notebooks that are notable. Feel free to add new content here, but please try to only include …

Searchable Datasets in Python: Images across Domains, Experiments, Algorithms, and Learning

When you hear about searching, chances are the first image that pops into your mind is a web browser and a web search engine. From ancient Alta Vista …

Why is Python so popular for data science?

All the major projects in deep-learning and neural networks are seeming to converge on Python as a glue language. As a long time Python engineer, I …

SQL Holds Its Own in Lucrative Data Science Field

Contradicting a popular view that sees programming languages such as R, Python and Java as the top tools for data science (which has been dubbed the …

7 More Steps to Mastering Machine Learning With Python

<b>By Matthew Mayo, KDnuggets.</b><p>So, you have been thinking about picking up machine learning, but given the confusing state of the web you don't know …

Artificial data give the same results as real data — without compromising privacy

Although data scientists can gain great insights from large data sets — and can ultimately use these insights to tackle major challenges — …

What if depression serves a purpose?

A new hypothesis sheds light on an age-old mental health issue.<p>Depression is so common — about 1 out of every 6 people experience it during their …

Quantifying controversy in social media

Quantifying controversy in social media Garimella et al. <i>WSDM 2016</i>Last week I had the pleasure of dropping in on WSDM (Web Search & Data Mining) 2017 …

Semantic Question Matching with Deep Learning

<i>Authors:</i> <i>Lili Jiang</i><i>,</i> <i>Shuo Chang</i><i>, and</i> <i>Nikhil Dandekar</i> <br>In order to build a high-quality knowledge base, it's important that we ensure each unique question …

Lasso regression etc in Stan

Someone on the users list asked about lasso regression in Stan, and Ben replied:In the rstanarm package we have stan_lm(), which is sort of like …

Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)

<b>tl;dr:</b> <i>GANs are simpler to set up than you think</i><p>In 2014, Ian Goodfellow and his colleagues at the University of Montreal published a stunning paper …

Measurement error and the replication crisis

Alison McCook from Retraction Watch interviewed Eric Loken and me regarding our recent article, “Measurement error and the replication crisis.” We …