Rapidly learning from ongoing experiences and remembering past events with a flexible memory system are two core capacities of biological intelligence. While the underlying neural mechanisms are not fully understood, various evidence supports that synaptic plasticity plays a critical role in memory formation and fast learning. Inspired by these results, we equip Recurrent Neural Networks (RNNs) with plasticity rules to enable them to adapt their parameters according to ongoing experiences. In addition to the traditional local Hebbian plasticity, we propose a global, gradient-based plasticity rule, which allows the model to evolve towards its self-determined target. Our models show promising results on sequential and associative memory tasks, illustrating their ability to robustly form and retain memories. In the meantime, these models can cope with many challenging few-shot learning problems. Comparing different plasticity rules under the same framework shows that Hebbian plasticity is well-suited for several memory and associative learning tasks; however, it is outperformed by gradient-based plasticity on few-shot regression tasks which require the model to infer the underlying mapping. Code is available at https://github.com/yuvenduan/PlasticRNNs.
While annotating decent amounts of data to satisfy sophisticated learning models can be cost-prohibitive for many real-world applications. Active learning (AL) and semi-supervised learning (SSL) are two effective, but often isolated, means to alleviate the data-hungry problem. Some recent studies explored the potential of combining AL and SSL to better probe the unlabeled data. However, almost all these contemporary SSL-AL works use a simple combination strategy, ignoring SSL and AL's inherent relation. Further, other methods suffer from high computational costs when dealing with large-scale, high-dimensional datasets. Motivated by the industry practice of labeling data, we propose an innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i.e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL. We estimate unlabeled samples' inconsistency by augmentation strategies of different granularities, including fine-grained continuous perturbation exploration and coarse-grained data transformations. Extensive experiments, in both text and image domains, validate the effectiveness of the proposed algorithm, comparing it against state-of-the-art baselines. Two real-world case studies visualize the practical industrial value of applying and deploying the proposed data sampling algorithm.
This paper proposes a novel fixed inducing points online Bayesian calibration (FIPO-BC) algorithm to efficiently learn the model parameters using a benchmark database. The standard Bayesian calibration (STD-BC) algorithm provides a statistical method to calibrate the parameters of computationally expensive models. However, the STD-BC algorithm scales very badly with the number of data points and lacks online learning capability. The proposed FIPO-BC algorithm greatly improves the computational efficiency and enables the online calibration by executing the calibration on a set of predefined inducing points. To demonstrate the procedure of the FIPO-BC algorithm, two tests are performed, finding the optimal value and exploring the posterior distribution of 1) the parameter in a simple function, and 2) the high-wave number damping factor in a scale-resolving turbulence model (SAS-SST). The results (such as the calibrated model parameter and its posterior distribution) of FIPO-BC with different inducing points are compared to those of STD-BC. It is found that FIPO-BC and STD-BC can provide very similar results, once the predefined set of inducing point in FIPO-BC is sufficiently fine. But, the FIPO-BC algorithm is at least ten times faster than the STD-BC algorithm. Meanwhile, the online feature of the FIPO-BC allows continuous updating of the calibration outputs and potentially reduces the workload on generating the database.
Current neural Natural Language Generation (NLG) models cannot handle emerging conditions due to their joint end-to-end learning fashion. When the need for generating text under a new condition emerges, these techniques require not only sufficiently supplementary labeled data but also a full re-training of the existing model. In this paper, we present a new framework named Hierarchical Neural Auto-Encoder (HAE) toward flexible conditional text generation. HAE decouples the text generation module from the condition representation module to allow "one-to-many" conditional generation. When a fresh condition emerges, only a lightweight network needs to be trained and works as a plug-in for HAE, which is efficient and desirable for real-world applications. Extensive experiments demonstrate the superiority of HAE against the existing alternatives with much less training time and fewer model parameters.