andrehuang / NostalgicAdam-NosAdam
[IJCAI'19] Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate
☆12Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for NostalgicAdam-NosAdam
- DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks https://arxiv.org/abs/1901.09229☆66Updated 3 years ago
- Tensorflow Implementation on Paper [ECCV2018]Semi-Supervised Deep Learning with Memory☆47Updated 5 years ago
- Generalized Framework for PyTorch☆32Updated 2 years ago
- Capsule Projection Networks (CapProNet) in pytorch, NeurIPS 2018☆33Updated 5 years ago
- Code for the paper "Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets", ICCV 2019☆27Updated 4 years ago
- This project is the Torch implementation of our accepted AAAI 2018 paper : orthogonal weight normalization method for solving orthogonali…☆57Updated 4 years ago
- A PyTorch implementation for Unsupervised Data Augmentation☆23Updated 2 years ago
- ☆26Updated 6 years ago
- Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906☆48Updated 4 years ago
- pytorch implementation for paper, towards realistic predictors☆17Updated 6 years ago
- PyTorch implementation of "SNAPSHOT ENSEMBLES: TRAIN 1, GET M FOR FREE" [WIP]☆37Updated 7 years ago
- 97.39% on CIFAR10 with PyTorch☆15Updated 5 years ago
- PyTorch Vision Toolbox not only for deep-clustering☆29Updated 2 years ago
- Delta Orthogonal Initialization for PyTorch☆18Updated 6 years ago
- Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters☆30Updated 4 years ago
- ☆39Updated 6 years ago
- The official implementation of paper "DIANet:Dense-and-Implicit-Attention-Network".☆102Updated last year
- Training Neural Networks Without Gradients: A Scalable ADMM Approach python implement☆15Updated 7 years ago
- [ICCV 2019 oral] Code for Semi-Supervised Learning by Augmented Distribution Alignment☆62Updated 2 years ago
- ☆19Updated 5 years ago
- ☆53Updated 6 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- [TNNLS] Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling☆45Updated 4 years ago
- ICML'19: How does Disagreement Help Generalization against Label Corruption?☆21Updated 5 years ago
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference, Gal et al. 2015☆35Updated 6 years ago
- Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression☆47Updated last year
- PyTorch implementation for GAL.☆55Updated 4 years ago