Humans and most animals can learn new tasks without forgetting old ones. However, training artificial neural networks (ANNs) on new tasks typically cause it to forget previously learned tasks. This phenomenon is the result of "catastrophic forgetting", in which training an ANN disrupts connection weights that were important for solving previous tasks, degrading task performance. Several recent studies have proposed methods to stabilize connection weights of ANNs that are deemed most important for solving a task, which helps alleviate catastrophic forgetting. Here, drawing inspiration from algorithms that are believed to be implemented in vivo, we propose a complementary method: adding a context-dependent gating signal, such that only sparse, mostly non-overlapping patterns of units are active for any one task. This method is easy to implement, requires little computational overhead, and allows ANNs to maintain high performance across large numbers of sequentially presented tasks when combined with weight stabilization. This work provides another example of how neuroscience-inspired algorithms can benefit ANN design and capability.
We introduce natural adversarial examples -- real-world, unmodified, and naturally occurring examples that cause classifier accuracy to significantly degrade. We curate 7,500 natural adversarial examples and release them in an ImageNet classifier test set that we call ImageNet-A. This dataset serves as a new way to measure classifier robustness. Like l_p adversarial examples, ImageNet-A examples successfully transfer to unseen or black-box classifiers. For example, on ImageNet-A a DenseNet-121 obtains around 2% accuracy, an accuracy drop of approximately 90%. Recovering this accuracy is not simple because ImageNet-A examples exploit deep flaws in current classifiers including their over-reliance on color, texture, and background cues. We observe that popular training techniques for improving robustness have little effect, but we show that some architectural changes can enhance robustness to natural adversarial examples. Future research is required to enable robust generalization to this hard ImageNet test set.
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible to the human eye. We further empirically analyze these universal perturbations and show, in particular, that they generalize very well across neural networks. The surprising existence of universal perturbations reveals important geometric correlations among the high-dimensional decision boundary of classifiers. It further outlines potential security breaches with the existence of single directions in the input space that adversaries can possibly exploit to break a classifier on most natural images.
This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new approach not only leverages the feature-based representation learned by a neural network from the initial task (representational transfer), but also information about the classes (concept transfer). The concept information is encapsulated in a probabilistic model for the final layer weights of the neural network which acts as a prior for probabilistic k-shot learning. We show that even a simple probabilistic model achieves state-of-the-art on a standard k-shot learning dataset by a large margin. Moreover, it is able to accurately model uncertainty, leading to well calibrated classifiers, and is easily extensible and flexible, unlike many recent approaches to k-shot learning.
Spare a thought for man's spurned best friends. Proud British pedigrees such as the Skye terrier, bloodhound and Dandie Dinmont are facing extinction -- rejected in favour of'It' breeds beloved of celebrities. A mere 28 Skye terriers were registered with the Kennel Club last year, along with 40 otterhounds, 53 bloodhounds, 49 Sussex spaniels and 84 King Charles spaniels. Such numbers are insufficient to protect their minuscule gene pools from inbred doom. Breeders believe a birth rate of 300 puppies a year is needed to guarantee a large enough pool for a healthy population.