Here is an academic paper list which contains the papers that SnowCloud.ai AI Research Lab considered to be very important, must read.
The reason of any paper to be selected in this list may be any of the following:
-
The paper had brought a paradigm shift in its own domain.
-
The paper contained vital parts which lead the appearance of papers in 1.
-
The SnowCloud AI Lab considered that the paper may cause a paradigm shift within 3-5 years.
SnowSelected is all you need.
- Long and Short-Term Memory : A well-known solution for long sentences processing.
- Learning Longer Memory in RNN
- RAM
- Encoder-Decoder for NLP
- Seq2Seq
- A Convolutional Neural Network for Modelling Sentences
- CNN on Sentence Classification
- Very Deep Convolutional Networks for Text Classification
- Neural Machine Translation by Jointly Learning to Align and Translate : Attention first introduced in NLP field.
- Attention is All You Need. : first transduction model relying entirely on self-attention to compute representations of its input and output without using RNNs or convolution.
- BERT
- Transformer-XL: Introduced relative positional encoding. Combined AR and AE models to BERT.
- XLNet : Introduced DAG while learning parameters in sentence segments. Resolve the problem may caused by excessive long sentence.
- AlexNet:The Beginning of Deep Learning
- First Attention Solution
- GoogLeNet
- VGG
- SPP Net
- Highway Networks
- ResNet
- Deep Neural Networks for Object Detection
- Faster RCNN
- UNet
- FlowNet and FlowNet2.0
- Stacked Hourglass
- YOLO9000
- Segmentation is All You Need