Aligning Logits Generatively for Principled Black-Box Knowledge Distillation in the Wild.

Black-Box Knowledge Distillation (B2KD) is a conservative task in cloud-to-edge model compression, emphasizing the protection of data privacy and model copyrights on both the cloud and edge. With invisible data and models hosted on the server, B2KD aims to utilize only the API queries of the teacher model's inference results in the cloud to effectively distill a lightweight student model deployed on edge devices. B2KD faces challenges such as limited Internet exchange and edge-cloud disparity in data distribution.

Generalized stability and associative memory of delayed recurrent neural networks with variable external input.

The generalized stability and associative memory of delayed recurrent neural networks with variable external inputs are investigated in this paper. Based on the comparison principle, the monostability of normal differentiable systems is established, which is extended to neural networks with variable external inputs. Furthermore, the coexistence of multiple equilibrium points in delayed recurrent neural networks is analyzed, and the number of stable equilibrium points is increased by extending the activation functions to enhance storage capacity.

Multiple semantic prompt for rehearsal-free continual learning.

Deep neural networks have achieved impressive achievements in many applications while suffering from catastrophic forgetting, which refers to drastic degradation in performance on former tasks when training on novel ones. Continual learning aims to address the issue. A simple but effective solution is to replay a subset of previous data, while it increases memory costs and may violate data privacy.

Enhanced Dual-Pattern Matching with Vision-Language Representation for out-of-Distribution Detection.

Out-of-distribution (OOD) detection presents a significant challenge in deploying pattern recognition and machine learning models, as they frequently fail to generalize to data from unseen distributions. Recent advancements in vision-language models (VLMs), particularly CLIP, have demonstrated promising results in OOD detection through their rich multimodal representations. However, current CLIP-based OOD detection methods predominantly rely on single-modality in-distribution (ID) data (e.

Leader-Following Consensus of Time-Scale-Type Heterogeneous Nonlinear MASs via Periodic Event-Triggered Control.

In this article, leader-following consensus of time-scale-type heterogeneous nonlinear multiagent systems (HNMASs) is investigated with dynamic periodic event-triggered mechanism (DPETM). The event detection period in DPETM is determined by a function-dependent threshold, whose initial value and the value at each periodic event detection instant are used for the update of an auxiliary function in the DPETM. Furthermore, the auxiliary function with periodic jumps serves as a detection threshold.

Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition.

Multimodal emotion recognition in conversation (MERC) has garnered substantial research attention recently. Existing MERC methods face several challenges: (1) they fail to fully harness direct inter-modal cues, possibly leading to less-than-thorough cross-modal modeling; (2) they concurrently extract information from the same and different modalities at each network layer, potentially triggering conflicts from the fusion of multi-source data; (3) they lack the agility required to detect dynamic sentimental changes, perhaps resulting in inaccurate classification of utterances with abrupt sentiment shifts. To address these issues, a novel approach named GraphSmile is proposed for tracking intricate emotional cues in multimodal dialogues.

A Trust-Region Projection Neural Network for Nonlinear Programming.

The trust-region method and projection neural networks are two branches of optimization approaches with different operational principles and characteristics. In this article, a trust-region projection neural network (TRPNN) is proposed by integrating the trust-region method and projection neural networks. TRPNN is a discrete-time neurodynamic optimization model that inherits the exploration-exploitation capability of the trust-region method and the local search capability of projection neural networks.

Event-Triggered Finite-Time Stabilization of Delayed T-S Fuzzy Systems on Time Scales.

In this article, the event-triggered finite-time stabilization of time-scale delayed Takagi-Sugeno (T-S) fuzzy systems is studied. By comparing strategies, inequality techniques, and time scale theory, finite-time stabilization criteria for the systems are derived that do not require differentiability of the time delay, and the controller is designed in a simple form that does not rely on power functions or delayed state feedback controllers. Corresponding results cover both continuous-time and discrete-time cases, and construct a unified theoretical framework for the finite-time analysis of the time-scale delayed systems.

Prompt-guided consistency learning for multi-label classification with incomplete labels.

Addressing insufficient supervision and improving model generalization are essential for multi-label classification with incomplete annotations, i.e., partial and single positive labels.

Natural Alkaloid Arecoline-Derived Amino Acid Derivatives: Design, Synthesis, and Evaluation of Their Antifungal Activity in an Agricultural Context.

A novel series of arecoline derivatives featuring amino acid moieties and 2-aminopyridine scaffolds was designed, synthesized, and assessed against seven phytopathogens. Compound emerged as the most potent derivative, exhibiting an EC of 10.2 μg/mL against , representing an approximately 50-fold improvement over the parent compound, arecoline.

ZIF-67-Embedded Polyacrylamide/Sodium Alginate/Polyacrylic Acid Hydrogel for Efficient and Selective Uranium Extraction.

The escalating global demand for nuclear energy has intensified the need for developing highly efficient and selective adsorbents for extraction of uranium from seawater. In this study, ZIF-67 is embedded into a polyacrylamide/sodium alginate/poly(acrylic acid) (PAM/SA/PAA) hydrogel through chelation and covalent cross-linking to prepare a novel PAM/SA/PAA@ZIF-67 (PSP@ZIF-67) adsorbent. PSP@ZIF-67 exhibits excellent uranium(VI) (U(VI)) adsorption performance.

Online Reinforcement Learning Control Designs With Acceleration Mechanism for Unknown Multiagent Systems Through Value Iteration.

In this article, an online reinforcement learning (RL) control method through value iteration (VI) is developed to solve the optimal cooperative control problem for the unknown linear discrete-time multiagent systems (MASs). On the one hand, an online learning scheme with evolving policies is proposed in order to guarantee the stability of the MASs under immature policies generated by VI. Inspired by the event-triggered mechanism, the stability criterion is designed as a trigger to filter the admissible control policies, which eliminates the need to establish a monotonic value function sequence.

Toosendanin promotes prostate cancer cell apoptosis, ferroptosis and M1 polarization via USP39-mediated PLK1 deubiquitination.

Toosendanin (TSN) can inhibit the malignant process of many cancers, and has the potential to be developed as an anti-tumor drug. However, the role and mechanism of TSN in prostate cancer (PCa) progression remain unclear. PCa cells (DU145 and LNCaP) were treated with TSN.

Semi-Global and Global Fixed-Time Stability for Nonlinear Impulsive Systems.

This study investigates the semi-global fixed-time stability (SGFTS) and global fixed-time stability (GFTS) of nonlinear impulsive systems (NISs). A key challenge in analyzing the SGFTS of such systems lies in the evolving integration methods caused by the impulses. To address this, we dynamically partition the semi-global attraction set (SGAS) and solve the corresponding differential equations within each subset.

Lyapunov-Based Safe Reinforcement Learning for Microgrid Energy Management.

The rapid development of renewable energy sources (RESs) has led to their increased integration into microgrids (MGs), emphasizing the need for safe and efficient energy management in MG operations. We investigate the methods of MG energy management, primarily categorized into model-based and model-free approaches. Due to a lack of incremental knowledge, model-based methods need to be reengineered for new scenarios during the optimization process, leading to reduced computational efficiency.

Synthesis and antifungal activity of arecoline derivatives containing amino acid fragments.

A series of new arecoline derivatives containing amino acid fragments were synthesized, and their fungicidal activities were investigated. All synthesized compounds were characterized by H NMR, CNMR, and HRMS. Preliminary bioactivity assays demonstrated that Compounds 3k, 3n, 3p, 3q, 3r, and 3s exhibited significant antifungal activity against Botryosphaeria cactivora, Botryosphaeria dothidea, and Fusarium pseudograminearum at a concentration of 100 μg/mL.

Multi-kernel feature extraction with dynamic fusion and downsampled residual feature embedding for predicting rice RNA N6-methyladenine sites.

RNA N$^{6}$-methyladenosine (m$^{6}$A) is a critical epigenetic modification closely related to rice growth, development, and stress response. m$^{6}$A accurate identification, directly related to precision rice breeding and improvement, is fundamental to revealing phenotype regulatory and molecular mechanisms. Faced on rice m$^{6}$A variable-length sequence, to input into the model, the maximum length padding and label encoding usually adapt to obtain the max-length padded sequence for prediction.

Memristor-based circuit design of BiLSTM network.

The bidirectional long short-term memory (BiLSTM) network involves significant amount of parameter computations. This paper proposes the memristor-based bidirectional long short-term memory (MBiLSTM) network, with its capability of in-memory computing and parallel computing, can accelerates the parameter computations speed. The MBiLSTM network circuit is composed of normalization circuit, two memristor-based long short-term memory (LSTM) circuits, memristor-based resnet circuit, memristor-based dense circuitand winner-take-all (WTA) circuit.

A Memristive Spiking Neural Network Circuit for Bio-Inspired Navigation Based on Spatial Cognitive Mechanisms.

Cognitive navigation, a high-level and crucial function for organisms' survival in nature, enables autonomous exploration and navigation within the environment. However, most existing works for bio-inspired navigation are implemented with non-neuromorphic computing. This work proposes a bio-inspired memristive spiking neural network (SNN) circuit for goal-oriented navigation, capable of online decision-making through reward-based learning.

Boosting Communication Efficiency in Federated Learning for Multiagent-Based Multimicrogrid Energy Management.

Privacy of user is becoming increasingly significant in constructing efficient multiagent energy management systems for multimicrogrid (MMG). As an emerging privacy-protection method, federated learning (FL) has been used to prevent data breaches in the MMG-related field. However, with the ever-growing participants, the underlying communication burden existing in FL is evident.

Unspecific peroxygenase enabled formation of azoxy compounds.

Enzymes are making a significant impact on chemical synthesis. However, the range of chemical products achievable through biocatalysis is still limited compared to the vast array of products possible with organic synthesis. For instance, azoxy products have rarely been synthesized using enzyme catalysts.

Mittag-Leffler stability and application of delayed fractional-order competitive neural networks.

In the article, the Mittag-Leffler stability and application of delayed fractional-order competitive neural networks (FOCNNs) are developed. By virtue of the operator pair, the conditions of the coexistence of equilibrium points (EPs) are discussed and analyzed for delayed FOCNNs, in which the derived conditions of coexistence improve the existing results. In particular, these conditions are simplified in FOCNNs with stepped activations.

Driving Cognitive Alertness Detecting Using Evoked Multimodal Physiological Signals Based on Uncertain Self-Supervised Learning.

Multimodal physiological signals play a pivotal role in drivers' perception of work stress. However, the scarcity of labels and the multitude of modalities render the utilization of physiological signals for driving cognitive alertness detection challenging. We thus propose a multimodal physiological signal detection model based on self-supervised learning.

A Bionic Localization Memristive Circuit Based on Spatial Cognitive Mechanisms of Hippocampus and Entorhinal Cortex.

In this article, a bionic localization memristive circuit is proposed, which mainly consists of head direction cell module, grid cell module, place cell module and decoding module. This work modifies the two-dimensional Continuous Attractor Network (CAN) model of grid cells into two one-dimensional models in X and Y directions. The head direction cell module utilizes memristors to integrate angular velocity and represents the real orientation of an agent.