Place recognition is an essential spatial intelligence capability for robots to understand and navigate the world. However, recognizing places in natural environments remains a challenging task for robots because of resource limitations and changing environments. In contrast, humans and animals can robustly and efficiently recognize hundreds of thousands of places in different conditions. Here, we report a brain-inspired general place recognition system, dubbed NeuroGPR, that enables robots to recognize places by mimicking the neural mechanism of multimodal sensing, encoding, and computing through a continuum of space and time. Our system consists of a multimodal hybrid neural network (MHNN) that encodes and integrates multimodal cues from both conventional and neuromorphic sensors. Specifically, to encode different sensory cues, we built various neural networks of spatial view cells, place cells, head direction cells, and time cells. To integrate these cues, we designed a multiscale liquid state machine that can process and fuse multimodal information effectively and asynchronously using diverse neuronal dynamics and bioinspired inhibitory circuits. We deployed the MHNN on Tianjic, a hybrid neuromorphic chip, and integrated it into a quadruped robot. Our results show that NeuroGPR achieves better performance compared with conventional and existing biologically inspired approaches, exhibiting robustness to diverse environmental uncertainty, including perceptual aliasing, motion blur, light, or weather changes. Running NeuroGPR as an overall multi–neural network workload on Tianjic showcases its advantages with 10.5 times lower latency and 43.6% lower power consumption than the commonly used mobile robot processor Jetson Xavier NX.

Synaptic plasticity plays a critical role in the expression power of brain neural networks. Among diverse plasticity rules, synaptic scaling presents indispensable effects on homeostasis maintenance and synaptic strength regulation. In the current modeling of brain-inspired spiking neural networks (SNN), backpropagation through time is widely adopted because it can achieve high performance using a small number of time steps. Nevertheless, the synaptic scaling mechanism has not yet been well touched. In this work, we propose an experience-dependent adaptive synaptic scaling mechanism (AS-SNN) for spiking neural networks. The learning process has two stages: First, in the forward path, adaptive short-term potentiation or depression is triggered for each synapse according to afferent stimuli intensity accumulated by presynaptic historical neural activities. Second, in the backward path, long-term consolidation is executed through gradient signals regulated by the corresponding scaling factor. This mechanism shapes the pattern selectivity of synapses and the information transfer they mediate. We theoretically prove that the proposed adaptive synaptic scaling function follows a contraction map and finally converges to an expected fixed point, in accordance with state-of-the-art results in three tasks on perturbation resistance, continual learning, and graph learning. Specifically, for the perturbation resistance and continual learning tasks, our approach improves the accuracy on the N-MNIST benchmark over the baseline by 44% and 25%, respectively. An expected firing rate callback and sparse coding can be observed in graph learning. Extensive experiments on ablation study and cost evaluation evidence the effectiveness and efficiency of our nonparametric adaptive scaling method, which demonstrates the great potential of SNN in continual learning and robust learning.

Digital nucleic acid amplification testing (dNAAT)-including digital PCR and isothermal techniques-has transformed precision diagnostics by enabling single-molecule quantification. However, its widespread adoption in point-of-care testing (POCT) remains limited by challenges in partitioning diversity, signal interpretation, and workflow integration. In this review, we provide the first systematic synthesis of artificial intelligence (AI)-driven fluorescence image analysis in dNAAT, detailing the evolution from classical classifiers to modern deep learning and foundation models (e.g., SAM, ViT, GPT-4o). We propose a structured framework that redefines dNAAT into five stages: Sample Preparation, Partition, Amplification, Detection, and Analysis, highlighting advancements enhancing precision, scalability, and automation at each step. The review also surveys integrated system prototypes for POCT and explores translational opportunities for AI-native platforms. Finally, we discuss key limitations-including data scarcity and model generalizability-and outline future research directions toward democratized molecular diagnostics.

Considering the importance of capturing both global conversational topics and local speaker dependencies for multimodal emotion recognition in conversations, current approaches first utilize sequence models like Transformer to extract global context information, then apply Graph Neural Networks to model local speaker dependencies for local context information extraction, coupled with Graph Contrastive Learning (GCL) to enhance node representation learning. However, this sequential design introduces potential biases: the extracted global context information inevitably influences subsequent processing, compromising the independence and diversity of the original local features; current graph augmentation methods in GCL cannot consider both global and local context information in conversations to evaluate the node importance, hindering the learning of key information. Inspired by the human brain excels at handling complex tasks by efficiently integrating local and global information processing mechanisms, we propose an aligned global-local context fusion framework for sequence-based design to address these problems. This design includes a dual-attention Transformer and a dual-evaluation method for graph augmentation in GCL. The dual-attention Transformer combines global attention for overall context extraction with sliding-window attention for local context capture, both enhanced by spiking neuron dynamics. The dual-evaluation method in GCL comprises global importance evaluation to identify nodes crucial for overall conversation context, and local importance evaluation to detect nodes significant for local semantics, generating augmented graph views that preserve both global and local information. This approach ensures balanced information processing throughout the pipeline, enhancing biological plausibility and achieving superior emotion recognition.

Yusong Wang, Dongyuan Li, Jialun Shen, Yicheng Xu, Mingkun Xu, Kotaro Funakoshi, Manabu Okumura. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

Semi-supervised graph learning (SSL) is an important task in machine learning that aims to make predictions based on a limited amount of labeled data and a larger set of unlabeled structured data, which can be effectively processed by biological neural networks. In this paper, we investigate the effects of the underlying homeostatic synaptic modulation (HSM) in spiking neural networks (SNNs) on such scenario. We propose a novel framework that integrates HSM into the spiking graph convolutional network to maintain stability by regulating the strength of synapses based on the activity of neurons, allowing for stable graph learning in a semi-supervised setting. Experimental results on citation benchmark datasets demonstrate that the proposed HSM mechanism can enable SNNs with superior capabilities of convergence and generalization, meanwhile possessing expected characteristics of sparsity and call-back phenomenon. The proposed framework provides a promising approach for exploiting HSM in neural network architectures for efficient graph learning.