- [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.
- [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.
- ML beyond Curve Fitting: An Intro to Causal Inference and do-Calculus
- [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.
- Lawrence Hidden Valley Camp
- Review: Half a year later, the Google Pixel 2 XL has proven itself a worthy successor | 9to5Google
- NervanaSystems · GitHub
Intel
- Intel AI Lab open-sources library for deep learning-driven NLP | VentureBeat
- Scientists discovered massive hidden canyons in Antarctica that could spell bad news for the rest of the planet – Quartz
- ICE Plans to Start Destroying Records of Immigrant Abuse, Including Sexual Assault and Deaths in Custody | American Civil Liberties Union
- Federal Agencies Lost Track of Nearly 1,500 Migrant Children Placed With Sponsors – The New York Times
- ROBIN’S BOOKS | Shoving Books Into Readers’ Hands Since 1958
- Here’s Amazon’s explanation for the Alexa eavesdropping scandal – Recode
- 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
- Behind the Scenes of Harvey Weinstein’s Impending Arrest | The New Yorker
- Roaring Forties Blue | Murray’s Cheese
- FBI repeatedly overstated encryption threat figures to Congress, public – The Washington Post
- Opinion | The Democrats’ Midterm Dilemma – The New York Times
- 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.
- 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.
- Meredith Lee on Twitter: "Calling all #opendata #waterwednesday #openscience #collaboration enthusiasts: join the #CAWaterDataChallenge now💧📈 https://t.co/MRIBxcV5Vp… https://t.co/4HzF3vN5ne"
- [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.
Digest powered by RSS Digest