Dzmitry Bahdanau and colleagues, 2015
We conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture.
Don't Just Read it – Explore It
We conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture.
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks.
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
We present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure.
We present YOLO, a new approach to object detection.
Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features.
We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously.
The key idea is to randomly drop units (along with their connections) from the neural network during training.
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.
We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments.
Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch.
The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting.