Skip to search formSkip to main contentSkip to account menu
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
TLDR
Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits.
View PDF on arXiv
Contextual String Embeddings for Sequence Labeling
TLDR
This paper proposes to leverage the internal states of a trained character language model to produce a novel type of word embedding which they refer to as contextual string embeddings, which are fundamentally model words as sequences of characters and are contextualized by their surrounding text.
View on ACL
FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP
TLDR
The core idea of the FLAIR framework is to present a simple, unified interface for conceptually very different types of word and document embeddings, which effectively hides all embedding-specific engineering complexity and allows researchers to “mix and match” variousembeddings with little effort.
View on ACL
Pooled Contextualized Embeddings for Named Entity Recognition
TLDR
This work proposes a method in which it dynamically aggregate contextualized embeddings of each unique string that the authors encounter and uses a pooling operation to distill a ”global” word representation from all contextualized instances.
View on ACL
Learning Texture Manifolds with the Periodic Spatial GAN
TLDR
It is shown that the image generation with PSGANs has properties of a texture manifold: it can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset.
View PDF on arXiv
Texture Synthesis with Spatial Generative Adversarial Networks
TLDR
This is the first successful completely data-driven texture synthesis method based on GANs, and has the following features which make it a state of the art algorithm for texture synthesis: high image quality of the generated textures, very high scalability w.r.t. the output texture size, fast real-time forward generation.
View PDF on arXiv
Quadratic optimization for simultaneous matrix diagonalization
TLDR
This paper presents a new algorithm called QDIAG that splits the overall optimization problem into a sequence of simpler second order subproblems and applies the new method to second-order blind source separation and shows that the algorithm converges fast and reliably.
View on IEEE
Multi-variate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
TLDR
This work model the multi-variate temporal dynamics of time series via an autoregressive deep learning model, where the data distribution is represented by a conditioned normalizing flow, which improves over the state-of-the-art for standard metrics on many real-world data sets with several thousand interacting time-series.
View PDF on arXiv
From grids to places
TLDR
It is shown that a simple linear transformation maximizing sparseness leads to a localized representation similar to place fields in grid cells in the medial entorhinal cortex of the dMEC.
View on Springer
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
TLDR
TimeGrad, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient, is proposed.
View PDF on arXiv
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License