**machine_learning**13334

Deep learning for tabular data - MachineLearning

3 hours ago by parzonka

It depends on whether your data have a natural temporal or spatial dimension.

Example 1. Your tabular could be a snapshot of a time-series. Then you can apply convolution or recurrence on that dimension of time.

Example 2. If your tabular data has position variables (such sensor geolocation), then you can project other variables in the space spanning these positions and apply convolution or recurrence on these dimensions.

machine_learning
deep_learning
tabular_data
Example 1. Your tabular could be a snapshot of a time-series. Then you can apply convolution or recurrence on that dimension of time.

Example 2. If your tabular data has position variables (such sensor geolocation), then you can project other variables in the space spanning these positions and apply convolution or recurrence on these dimensions.

3 hours ago by parzonka

[1805.09501] AutoAugment: Learning Augmentation Policies from Data

20 hours ago by amy

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
20 hours ago by amy

[1805.09692] Been There, Done That: Meta-Learning with Episodic Recall

20 hours ago by amy

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
20 hours ago by amy

[1705.07538] Infrastructure for Usable Machine Learning: The Stanford DAWN Project

20 hours ago by amy

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
20 hours ago by amy

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.

yesterday by amy

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
yesterday by amy

[1802.06765] Interpretable VAEs for nonlinear group factor analysis

yesterday by amy

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
yesterday by amy

Education – Google AI

2 days ago by ricgrego

cursos de Artificial Intelligence / Machine Learning

data_science
ai
machine_learning
cursos
acadêmico
principais
google
2 days ago by ricgrego

[1805.08498] Implicit Reparameterization Gradients

2 days ago by amy

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
2 days ago by amy

**related tags**

Copy this bookmark: