• Publications
  • Influence
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
TLDR
We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. Expand
  • 2,428
  • 661
  • PDF
Contextual String Embeddings for Sequence Labeling
TLDR
We propose to leverage the internal states of a trained character language model to produce a novel type of word embedding which we refer to as contextual string embeddings. Expand
  • 597
  • 150
  • PDF
FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP
TLDR
We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models. Expand
  • 161
  • 35
  • PDF
Pooled Contextualized Embeddings for Named Entity Recognition
TLDR
We propose a method in which we dynamically aggregate contextualized embeddings of each unique string that we encounter. Expand
  • 131
  • 26
  • PDF
Texture Synthesis with Spatial Generative Adversarial Networks
TLDR
We introduce a new model for texture synthesis based on GAN learning based on spatial GANs. Expand
  • 107
  • 15
  • PDF
Quadratic optimization for simultaneous matrix diagonalization
TLDR
In this paper, we present a new algorithm called QDIAG that splits the overall optimization problem into a sequence of simpler second order subproblems and show that the algorithm converges fast and reliably. Expand
  • 96
  • 14
  • PDF
Learning Texture Manifolds with the Periodic Spatial GAN
TLDR
This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014). Expand
  • 74
  • 12
  • PDF
From grids to places
TLDR
We show that, starting with simulated grid-cells, a simple linear transformation maximizing sparseness leads to a localized representation similar to place fields. Expand
  • 64
  • 8
  • PDF
Multi-variate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
TLDR
We propose a probabilistic method to model multi-variate temporal dynamics of time series via an autoregressive deep learning model, where the data distribution is represented by a conditioned normalizing flow. Expand
  • 8
  • 2
  • PDF
Improved optimal linear filters for the discrimination of multichannel waveform templates for spike-sorting applications
TLDR
We derived optimal multichannel filters for waveform template discrimination in the time domain and compared their performance to those derived in the frequency domain. Expand
  • 23
  • 1
...
1
2
3
4
...