Oceania
MND left her without a voice. Eight seconds of scratchy audio gave it back to her
MND left her without a voice. After such a long time, I couldn't really remember my voice, Sarah Ezekiel tells BBC Access All. When I first heard it again, I felt like crying. The onset of motor neurone disease (MND) left Sarah without a voice and the use of her hands at the age of 34. It was within months of her becoming a mum for the second time.
A Universally Optimal Multistage Accelerated Stochastic Gradient Method
Necdet Serhat Aybat, Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar
Neural Information Processing Systems http://nips.cc/
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Tingting Qiao, Jing Zhang, Duanqing Xu, Dacheng Tao
Humans, however, tackle this problem intelligently.
A Primal-Dual Formulation for Deep Learning with Constraints
Since the constraints are independent of the target labels, our framework easily generalizes to semi-supervised setting.
Bayesian Optimization with Unknown Search Space
Huong Ha, Santu Rana, Sunil Gupta, Thanh Nguyen, Hung Tran-The, Svetha Venkatesh
Neural Information Processing Systems http://nips.cc/
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
Xinyang Chen, Sinan Wang, Bo Fu, Mingsheng Long, Jianmin Wang
Neural Information Processing Systems http://nips.cc/
A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning
Francisco Garcia, Philip S. Thomas
Neural Information Processing Systems http://nips.cc/
Explanations can be manipulated and geometry is to blame
Ann-Kathrin Dombrowski, Maximillian Alber, Christopher Anders, Marcel Ackermann, Klaus-Robert Mรผller, Pan Kessel
Neural Information Processing Systems http://nips.cc/
Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization
Yujiao Shi, Liu Liu, Xin Yu, Hongdong Li
One of the key reasons is the vast differences between the two view modalities, i.e.,
Visualizing the PHATE of Neural Networks
Scott Gigante, Adam S. Charles, Smita Krishnaswamy, Gal Mishne
We demonstrate that our visualization provides intuitive, detailed summaries of the learning dynamics beyond simple global measures (i.e., validation loss and accuracy), without the need to access validation data. Furthermore, M-PHA TE better captures both the dynamics and community structure of the hidden units as compared to visualization based on standard dimensionality reduction methods (e.g., ISOMAP, t-SNE). We demonstrate M-PHA TE with two vignettes: continual learning and generalization.