Deep Neural Networks (DNNs) have primarily been demonstrated to be useful for closed-world classification problems where the number of categories is fixed. However, DNNs notoriously fail when tasked with label prediction in a non-stationary data stream scenario, which has the continuous emergence of the unknown or novel class (categories not in the training set). For example, new topics continually emerge in social media or e-commerce. To solve this challenge, a DNN should not only be able to detect the novel class effectively but also incrementally learn new concepts from limited samples over time. Literature that addresses both problems simultaneously is limited. In this paper, we focus on improving the generalization of the model on the novel classes, and making the model continually learn from only a few samples from the novel categories. Different from existing approaches that rely on abundant labeled instances to re-train/update the model, we propose a new approach based on Few Sample and Adversarial Representation Learning (FSAR). The key novelty is that we introduce the adversarial confusion term into both the representation learning and few-sample learning process, which reduces the over-confidence of the model on the seen classes, further enhance the generalization of the model to detect and learn new categories with only a few samples. We train the FSAR operated in two stages: first, FSAR learns an intra-class compacted and inter-class separated feature embedding to detect the novel classes; next, we collect a few labeled samples belong to the new categories, utilize episode-training to exploit the intrinsic features for few-sample learning. We evaluated FSAR on different datasets, using extensive experimental results from various simulated stream benchmarks to show that FSAR effectively outperforms current state-of-the-art approaches.

The impact of population structure on evolving populations is difficult to study. Populations broken up into groups of organisms and connected by low levels of migration will experience different types of geneflow than normal unstructured populations. Various studies, spanning decades of research, have lead to seemingly contradictory conclusions. Some point to population structure as a means to improve adaptation, others argue that population structure hinders evolution. We investigate how population structure impacts the evolution of complex functions in environments with limited resources. We find that structured populations with limited resources tend to evolve complex functions at a higher rate than unstructured populations, across a broad range of migration rates. This suggests that population structure may have an important impact on evolution, in both sexual and asexual populations, at least at certain migration rates.