Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMarch 2024
Dual states based reinforcement learning for fast MR scan and image reconstruction
AbstractIncomplete phase encoding with few phases is an effective under-sampling manner of fast Magnetic Resonance (MR) scan. The key is how to choose important slice-specific phases. Reinforcement Learning (RL) is powerful for sequential decision-making ...
- articleMarch 2024
cpp-AIF: A multi-core C++ implementation of Active Inference for Partially Observable Markov Decision Processes
AbstractActive Inference is a computational framework used in neuroscience and cognitive science that characterises perception, planning and action in terms of probabilistic inference and the minimisation of variational free energy. cpp-AIF is a header-...
- research-articleMarch 2024
RoFormer: Enhanced transformer with Rotary Position Embedding
AbstractPosition encoding has recently been shown to be effective in transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various ...
- research-articleMarch 2024
Rotation-equivariant correspondence matching based on a dual-activation mixer
AbstractLearning-based correspondence matching methods have become the mainstream techniques in many computer vision and robotics applications due to their robustness to large illumination and viewpoint changes. However, it is difficult for conventional ...
- research-articleMarch 2024
Stable approximate Q-learning under discounted cost for data-based adaptive tracking control
AbstractIn this paper, the stability of tracking error dynamics under the data-based discounted iterative Q-learning is investigated. First, a novel performance index with a discount factor is introduced into the iterative Q-learning-based tracking ...
-
- research-articleMarch 2024
Dynamic event-triggered-based online IRL algorithm for the decentralized control of the input and state constrained large-scale unmatched interconnected system
AbstractThis article proposed a novel adaptive decentralized control (ADC) method for the continuous-time state-constrained and input-constrained large-scale unmatched interconnection system by the means of the adaptive critic design in the edge dynamic ...
Highlights- The state-constrained and input-constrained problems are simultaneously considered.
- In online IRL algorithm, the constrained system dynamic can be partially unknown.
- The EDET mechanism is devised to replace the traditional SET ...
- research-articleMarch 2024
Stabilization and synchronization control for discrete-time complex networks via the auxiliary role of edges subsystem
AbstractIn this paper, a novel discrete-time interconnected model composed of nodes and edges subsystems is proposed, to depict the complex dynamical networks (CDNs) consisted of nodes and dynamic edges which are coupled mutually. Firstly, we propose a ...
- research-articleMarch 2024
Decentralized optimal control of large-scale partially unknown nonlinear mismatched interconnected systems based on dynamic event-triggered control
AbstractIn this paper, a novel decentralized control method is proposed for nonlinear mismatched large-scale interconnected systems subjected to partially unknown dynamics by designing auxiliary control for each subsystem. It is demonstrated that the ...
Highlights- Edge dynamic event-triggered control is first time combined with IRL algorithms.
- The IRL algorithm relaxes the requirement of the system drift dynamics.
- Edge dynamic event-triggered method has better performance than static ...
- research-articleMarch 2024
Hyperbolic function-based fixed/preassigned-time stability of nonlinear systems and synchronization of delayed fuzzy Cohen–Grossberg neural networks
AbstractIn this article, the fixed-time (FIT) and preassigned-time (PRT) stability of nonlinear models and the FIT/PRT synchronization of discontinuous delayed fuzzy Cohen–Grossberg neural networks (DFCGNNs) are explored, respectively. Firstly, by means ...
- research-articleMarch 2024
Fault-tolerant tracking control for nonlinear systems with multiplicative actuator faults in view of zero-sum differential games
AbstractIn view of zero-sum differential games, this paper addresses the fault-tolerant tracking control (FTTC) problem for nonlinear systems with multiplicative actuator faults. By augmenting the nominal system, the trajectory tracking problem is ...
- research-articleMarch 2024
Neural dynamics solver for time-dependent infinity-norm optimization based on ACP framework with robot application
AbstractIn general, infinity-norm optimization (INO) is commonly deemed as a subset of nonlinear optimization. In the last decade, there have been relatively few reports on solving INO problems, specifically from the time-dependent aspect originating ...
- research-articleMarch 2024
Towards better transition modeling in recurrent neural networks: The case of sign language tokenization
AbstractRecurrent neural networks (RNNs) are a popular family of models widely used when facing sequential data such as videos. However, RNNs make assumptions about state transitions that could be damageable. This paper presents two theoretical ...
Highlights- Sign language tokenization is a challenging task involving complex transitions.
- The limitations of RNNs highlighted in theory can be observed in practice.
- Extensions have a positive impact, but there is still room for improvement.
- research-articleMarch 2024
Finite-time quasi-synchronization of multi-layer heterogeneous networks with distributed hybrid control
AbstractIn this paper, the finite-time quasi-synchronization of a multi-layer heterogeneous network with a leader node is studied. A novel distributed control approach that incorporates impulsive control is introduced to achieve finite-time quasi-...
- research-articleMarch 2024
Relphormer: Relational Graph Transformer for Knowledge Graph Representations
AbstractTransformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the Knowledge ...
- research-articleMarch 2024
Adjustable privacy using autoencoder-based learning structure
AbstractInference centers need more data to have a more comprehensive and beneficial learning model, and for this purpose, they need to collect data from data providers. On the other hand, data providers are cautious about delivering their datasets to ...
- research-articleMarch 2024
Robust learning of parsimonious deep neural networks
AbstractWe propose a simultaneous learning and pruning algorithm capable of identifying and eliminating irrelevant structures in a neural network during the early stages of training. Simultaneous learning and pruning presents serious challenges such as ...
- research-articleFebruary 2024
Attention Round for post-training quantization
AbstractQuantization methods for convolutional neural network models can be broadly categorized into post-training quantization (PTQ) and quantization aware training (QAT). While PTQ offers the advantage of requiring only a small portion of the data for ...
Highlights- Attention Round quantization function expands the quantization optimization space.
- Mixed precision allocation method improves mixed precision quantization efficiency.
- Enriched lightweight CNNs contribute to applications in resource-...
- research-articleFebruary 2024
Neuron importance based verification of neural networks via divide and conquer
AbstractNeural networks are widely used in various applications such as image classification, speech recognition and natural language processing. As intelligent systems often rely on neural networks to make critical decisions, it is crucial to ensure ...
- research-articleFebruary 2024
Spiking Neural Network with plasticity in the time domain recovers temporal information from a noisy pattern using reference spikes
AbstractNeurons in the brain communicate with each other by sending trains of spikes that can encode information using the timings of the spikes. Spiking Neural Networks (SNNs) are biologically plausible neural networks that can model this transfer of ...
Highlights- We propose reference spikes as new plastic parameters for spiking neural networks.
- The number and timings of reference spikes are modifiable by learning rules.
- Network with reference spikes can restore a spike pattern in a noise ...
- research-articleFebruary 2024
Personalized robotic control via constrained multi-objective reinforcement learning
AbstractReinforcement learning is capable of providing state-of-art performance in end-to-end robotic control tasks. Nevertheless, many real-world control tasks necessitate the balancing of multiple conflicting objectives while simultaneously ensuring ...
Graphical abstractDisplay Omitted
Highlights- A constrained multi-objective reinforcement learning approach is proposed.
- The method is formulated as a constrained multi-objective Markov decision process.
- An evenness metric is designed through Shannon–Wiener diversity index.