Exploiting noise as a resource for computation and learning in spiking neural networks.

Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy SNN (NSNN) and the noise-driven learning (NDL) rule by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. The NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation and learning. We demonstrate that this framework leads to spiking neural models with competitive performance, improved robustness against challenging perturbations compared with deterministic SNNs, and better reproducing probabilistic computation in neural coding. Generally, this study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers.

Dual memory model for experience-once task-incremental lifelong learning.

Experience replay (ER) is a widely-adopted neuroscience-inspired method to perform lifelong learning. Nonetheless, existing ER-based approaches consider very coarse memory modules with simple memory and rehearsal mechanisms that cannot fully exploit the potential of memory replay. Evidence from neuroscience has provided fine-grained memory and rehearsal mechanisms, such as the dual-store memory system consisting of PFC-HC circuits. However, the computational abstraction of these processes is still very challenging. To address these problems, we introduce the Dual-Memory (Dual-MEM) model emulating the memorization, consolidation, and rehearsal process in the PFC-HC dual-store memory circuit. Dual-MEM maintains an incrementally updated short-term memory to benefit current-task learning. At the end of the current task, short-term memories will be consolidated into long-term ones for future rehearsal to alleviate forgetting. For the Dual-MEM optimization, we propose two learning policies that emulate different memory retrieval strategies: Direct Retrieval Learning and Mixup Retrieval Learning. Extensive evaluations on eight benchmarks demonstrate that Dual-MEM delivers compelling performance while maintaining high learning and memory utilization efficiencies under the challenging experience-once setting.

Bioimaging of Dissolvable Microneedle Arrays: Challenges and Opportunities.

The emergence of microneedle arrays (MNAs) as a novel, simple, and minimally invasive administration approach largely addresses the challenges of traditional drug delivery. In particular, the dissolvable MNAs act as a promising, multifarious, and well-controlled platform for micro-nanotransport in medical research and cosmetic formulation applications. The effective delivery mostly depends on the behavior of the MNAs penetrated into the body, and accurate assessment is urgently needed. Advanced imaging technologies offer high sensitivity and resolution visualization of cross-scale, multidimensional, and multiparameter information, which can be used as an important aid for the evaluation and development of new MNAs. The combination of MNA technology and imaging can generate considerable new knowledge in a cost-effective manner with regards to the pharmacokinetics and bioavailability of active substances for the treatment of various diseases. In addition, noninvasive imaging techniques allow rapid, receptive assessment of transdermal penetration and drug deposition in various tissues, which could greatly facilitate the translation of experimental MNAs into clinical application. Relying on the recent promising development of bioimaging, this review is aimed at summarizing the current status, challenges, and future perspective on in vivo assessment of MNA drug delivery by various imaging technologies.