- 運営しているクリエイター
#kaggle
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D. Cubuk, Quoc V. Le Google Brain SpecAugment は Google Brain チームから提案された speech recognition における spectrogram の data augmentation の手法.約 1 年前に(本記事を書いている現在は Jul. 2020)
The Lovasz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
Arxiv Tensorflow / Pytorch implementation Demo 1. Abstract 1-1. Loss function for direct optimization w.r.t Jaccard index 1-2. Optimizing the Jaccard index in a continuous optimization framework 1-3. Lovasz hinge loss: binary im
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
Arxiv Keras / Pytorch implementationDemo 1. Abstract 1-1. Improving accuracy by 3% over Smyl's winning solution in M4 competition. 1-2. M4 competition summary paper: https://www.sciencedirect.com/science/article/pii/S016920701930