casper-hansen / Activation-Functions-Search
☆31Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for Activation-Functions-Search
- Pytorch implementation of Neural Machine Translation with seq2seq and attention (en-zh)☆41Updated 5 years ago
- 一些不同的Attention机制代码☆20Updated 4 years ago
- Keras深度学习框架配置+Keras教程+Keras Trick☆33Updated 5 years ago
- This is our solution for WSDM - DiggSci 2020. We implemented a simple yet robust search pipeline which ranked 2nd in the validation set a…☆62Updated 4 years ago
- 《机器学习之类别不平衡问题》文章代码☆45Updated 5 years ago
- 天池精准医疗大赛——人工智能辅助糖尿病遗传风险预测, 代码及总结☆23Updated 6 years ago
- ☆10Updated 3 years ago
- 精简版NEZHA模型权重☆21Updated 3 years ago
- Dilate Gated Convolutional Neural Network For Machine Reading Comprehension☆39Updated 5 years ago
- 使用tensorflow.keras实现《动手学深度学习》☆10Updated 4 years ago
- Relation Classification via Convolutional Deep Neural Network☆13Updated 6 years ago
- RankNet算法介绍☆41Updated 6 years ago
- Source code for "Training Generative Adversarial Networks Via Turing Test".☆13Updated 4 years ago
- 2018云移杯景区口碑评价分值预测 7/1186☆11Updated 6 years ago
- reformer-pytorch中文版本,简单高效的生成模型。类似GPT2的效果☆16Updated last year
- 深度学习和NLP随笔☆25Updated 5 years ago
- 在Pytorch下,采用LSTM/C-LSTM/CNN等方法,对评论进行多标签分类☆31Updated 6 years ago
- Text classification models: cnn, self-attention, cnn-rnf, rnn-att, capsule-net. TensorFlow. Single GPU or multi GPU☆18Updated 4 years ago
- RAdam optimizer for keras☆71Updated 5 years ago
- AI Challenger 2018 阅读理解赛道代码分享☆20Updated 5 years ago
- Adversarial Training for NLP in Keras☆46Updated 4 years ago
- Stochastic Weight Averaging in Keras☆10Updated 6 years ago
- 用户画像,知识图谱挖掘☆10Updated last year
- NLP Project + pytorch☆10Updated 4 years ago
- adafactor optimizer for keras☆20Updated 3 years ago
- Keras based Reading Comprehension Models☆18Updated 5 years ago
- Linear chain conditional random fields are implemented using Numpy and Mxnet/Gluon, and batch training is supported, not limited to train…☆24Updated 5 years ago
- 基 于BERT的预训练语言模型实现,分为两步:预训练和微调。目前已包括BERT、Roberta、ALbert三个模型,且皆可支持Whole Word Mask模式。☆16Updated 4 years ago
- The code of Encoding Word Order in Complex-valued Embedding☆42Updated 5 years ago