Deep Learning
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models Andy Zhou
One of the goals of machine learning is to develop systems that can generalize effectively across diverse populations and environments, much like human intelligence.
A Simple Cache Model for Image Recognition
Neural Information Processing Systems http://nips.cc/
Entropy and mutual information in models of deep neural networks
Marylou Gabriรฉ, Andre Manoel, Clรฉment Luneau, jean barbier, Nicolas Macris, Florent Krzakala, Lenka Zdeborovรก
Neural Information Processing Systems http://nips.cc/
GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence
Then we could generally binarize the reduced feature map before fed into the GUST.
Task-Driven Convolutional Recurrent Models of the Visual System
Aran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. Yamins
Neural Information Processing Systems http://nips.cc/
LearningLatentSeasonal-TrendRepresentationsfor TimeSeriesForecasting
However, clear patterns are still hard to extract since time series are often composed of several intricately entangled components.