58311
YouTube

llen Toussaint - American Tune (Live on Austin City Limits)
yesterday
YouTube

Simon & Garfunkel - American Tune (from The Concert in Central Park)
yesterday
Alitas | Agencies & Ministries | Catholic Community Services of Southern AZ

You can donate to Casa Alitas in Tucson, which provides care, short-term shelter and help to reunite with family members in the U.S. https://www.ccs-soaz.org/agencies-ministries/detail/alitas-aid-for-migrant-women-and-children
yesterday
[1805.09501] AutoAugment: Learning Augmentation Policies from Data
In this paper, we take a closer look at data augmentation for images, and describe a simple procedure called AutoAugment to search for improved data augmentation policies. Our key insight is to create a search space of data augmentation policies, evaluating the quality of a particular policy directly on the dataset of interest. In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.54%. On CIFAR-10, we achieve an error rate of 1.48%, which is 0.65% better than the previous state-of-the-art. On reduced data settings, AutoAugment performs comparably to semi-supervised methods without using any unlabeled examples. Finally, policies learned from one dataset can be transferred to work well on other similar datasets. For example, the policy learned on ImageNet allows us to achieve state-of-the-art accuracy on the fine grained visual classification dataset Stanford Cars, without fine-tuning weights pre-trained on additional data.
machine_learning 
yesterday
[1805.09692] Been There, Done That: Meta-Learning with Episodic Recall
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discovered solutions. We propose a formalism for generating open-ended yet repetitious environments, then develop a meta-learning architecture for solving these environments. This architecture melds the standard LSTM working memory with a differentiable neural episodic memory. We explore the capabilities of agents with this episodic LSTM in five meta-learning environments with reoccurring tasks, ranging from bandits to navigation and stochastic sequential decision problems.
machine_learning 
yesterday
[1705.07538] Infrastructure for Usable Machine Learning: The Stanford DAWN Project
Despite incredible recent advances in machine learning, building machine learning applications remains prohibitively time-consuming and expensive for all but the best-trained, best-funded engineering organizations. This expense comes not from a need for new and improved statistical models but instead from a lack of systems and tools for supporting end-to-end machine learning application development, from data preparation and labeling to productionization and monitoring. In this document, we outline opportunities for infrastructure supporting usable, end-to-end machine learning applications in the context of the nascent DAWN (Data Analytics for What's Next) project at Stanford.
machine_learning 
yesterday
Twitter
RT : This is an extraordinary scandal. One in five migrant kids recently placed by HHS into “foster care or whatever” h…
from twitter
2 days ago
Twitter
RT : The vast dump of plastic waste swirling in the Pacific ocean is now bigger than France, Germany and Spain combined:…
from twitter
2 days ago
Pacific plastic dump far larger than feared: study

The vast dump of plastic waste swirling in the Pacific ocean is now bigger than France, Germany and Spain combined: https://buff.ly/2FYy5hK

#EndOceanPlastic #UseLess #WasteLess https://twitter.com/MikeHudema/status/999626580971458560/photo/1
2 days ago
Instapaper says it will temporarily go offline in Europe due to GDPR | 9to5Mac

GDPR requires that users opt-in to all commercial use of personal data.
2 days ago
minimaxir/textgenrnn: Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
machine_learning 
2 days ago
[1802.06765] Interpretable VAEs for nonlinear group factor analysis
Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data. Far less attention has been paid to making these generative models interpretable. In many scenarios, ranging from scientific applications to finance, the observed variables have a natural grouping. It is often of interest to understand systems of interaction amongst these groups, and latent factor models (LFMs) are an attractive approach. However, traditional LFMs are limited by assuming a linear correlation structure. We present an output interpretable VAE (oi-VAE) for grouped data that models complex, nonlinear latent-to-observed relationships. We combine a structured VAE comprised of group-specific generators with a sparsity-inducing prior. We demonstrate that oi-VAE yields meaningful notions of interpretability in the analysis of motion capture and MEG data. We further show that in these situations, the regularization inherent to oi-VAE can actually lead to improved generalization and learned generative processes.
machine_learning  papers 
2 days ago
Manage Google Compute Engine with Node.js – Google Cloud Platform - Community – Medium
RT : Ever wondered if you can use to manage your virtual machines? Wonder no more! ✨🐢🚀✨
from twitter
2 days ago
Twitter
RT : 58 people shot, 851 people injured, and it seems like we've already forgotten about it. tries to fig…
from twitter
3 days ago
Donald Trump cannot block anyone on Twitter, court rules | US news | The Guardian

A district court in New York has ruled that Donald Trump cannot block people on Twitter, because it violates their first amendment rights to participate in a “public forum”.
3 days ago
Twitter
RT : questions that answer themselves
from twitter
3 days ago
Twitter
RT : Receive auto-prompts and in-line help for gcloud, gsutil, bq and kubectl commands as you type, using our new comman…
from twitter
3 days ago
Twitter
RT : New report by analyzes interviews with 50+ journalists to show how hate groups use manipu…
from twitter
3 days ago
[1805.08498] Implicit Reparameterization Gradients
By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models. However, it is not applicable to a number of important continuous distributions. We introduce an alternative approach to computing reparameterization gradients based on implicit differentiation and demonstrate its broader applicability by applying it to Gamma, Beta, Dirichlet, and von Mises distributions, which cannot be used with the classic reparameterization trick. Our experiments show that the proposed approach is faster and more accurate than the existing gradient estimators for these distributions.
machine_learning 
3 days ago
Twitter
A great and informative thread on TensorFlow eager execution mode (which if you haven’t encountered it, is super co…
from twitter
3 days ago
Twitter
RT : THE WOMEN ARE COMING
THE WOMEN ARE COMING
THE WOMEN ARE COMING
THE WOMEN ARE COMING
from twitter
3 days ago
Twitter
RT : Google Cloud Platform and Confluent partner to deliver a managed Apache Kafka service

Great…
from twitter
4 days ago
Untitled (https://www.nytimes.com/2018/05/21/world/europe/facebook-libel-paul-tweed.html)
RT : This is a good initiative from Facebook that probably won't have any unintended consequences
from twitter
4 days ago
Twitter
RT : This is a good initiative from Facebook that probably won't have any unintended consequences
from twitter
4 days ago
The statistical significance filter leads to overoptimistic expectations of replicability - Statistical Modeling, Causal Inference, and Social Science
Treating a result as publishable just because the p-value is less than 0.05 leads to overoptimistic expectations of replicability. These overoptimistic expectations arise due to Type M(agnitude) error: when underpowered studies yield significant results, effect size estimates are guaranteed to be exaggerated and noisy. These effects get published, leading to an overconfident belief in replicability. We demonstrate the adverse consequences of this statistical significance filter by conducting six direct replication attempts (168 participants in total) of published results from a recent paper. We show that the published claims are so noisy that even non-significant results are fully compatible with them. We also demonstrate the contrast between such small-sample studies and a larger-sample study (100 participants); the latter generally yields less noisy estimates but also a smaller effect size, which looks less compelling but is more realistic. We make several suggestions for improving best practices in psycholinguistics and related areas.
statistics 
4 days ago
Twitter
RT : Interpolating through the latent space of ramen dishes uses a GAN
from twitter
4 days ago
« earlier      
#ebook #gov20 #opengov @bbcscitech @brainpicker @daringfireball @ebertchicago @glynmoody @greatdismal @jscarroll @medicalnews @mindhackz @neuraxon77 @newscientist @pkedrosky @stilgherrian academia ack activism aggregator ai ajax amazon amusements analysis analytics animals api apple arghh art astronomy audio austin australia aws bigdata bigquery biology blogging blogs books business cats charity chocolate civil_liberties climate climate_change clothing cloud_computing coffee cognition comment communication computing cool css culture data database dataflow datamining design development distributed ebook ebooks ec2 economics economy education email environment essays evolution extensions feminism finance firefox food framework from gadgets gae gcp geekery gender genetics geolocation git global_warming golang google gov20 graphics gwt hadoop hardware health history internet interviews iphone iraq java javascript journalism k8s kansas kubernetes language law libraries mac machine_learning mapreduce maps md media medicine mobile movies music my nature neuroscience news nyc open_source opengov oscon osx pens philosophy photography photoshop php physics plugins politics presentations privacy productivity programming psychology python rails recipes reference religion research resources reviews rss ruby s3 scalability science search seattle security sent sex society software software/social statistics storage strataconf stuff sydney tagging tbr technology tensorflow texas tips tools travel tutorials tweets twitter twitter_fav typography uk usa utilities vegetarianism videos visualizations war web_app web_design web_dev web_services wishlist wordpress world writers writing

Copy this bookmark:



description:


tags: