Related papers: Excitability and memory in a time-delayed optoelec…
Due to their dynamic properties such as irregular sampling rate and high-frequency sampling, Continuous Time Series (CTS) are found in many applications. Since CTS with irregular sampling rate are difficult to model with standard Recurrent…
This paper presents a neurosymbolic framework to solve motion planning problems for mobile robots involving temporal goals. The temporal goals are described using temporal logic formulas such as Linear Temporal Logic (LTL) to capture…
Reinforcement Learning (RL) has been widely used to solve tasks where the environment consistently provides a dense reward value. However, in real-world scenarios, rewards can often be poorly defined or sparse. Auxiliary signals are…
The emergence of nano-scale memristive devices encouraged many different research areas to exploit their use in multiple applications. One of the proposed applications was to implement synaptic connections in bio-inspired neuromorphic…
The FitzHugh-Nagumo equation, originally conceived in neuroscience during the 1960s, became a key model providing a simplified view of excitable neuron cell behavior. Its applicability, however, extends beyond neuroscience into fields like…
Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods have improved prediction accuracy, few research efforts have…
Laser-induced acoustic desorption (LIAD) enables loading nanoparticles into optical traps under vacuum for levitated optomechanics experiments. Current LIAD systems rely on empirical optimization using available laboratory lasers rather…
Previous experiments in compensated magnets have demonstrated a potential for approaching the limit of fastest and least-dissipative operation of digital memory bits. However, the analog route has been virtually unexplored at (sub)ps time…
Highly efficient information processing in brain is based on processing and memory components called synapses, whose output is dependent on the history of the signals passed through them. Here we have developed an artificial synapse with…
We consider the Yamada model for an excitable or self-pulsating laser with saturable absorber, and study the effects of delayed optical self-feedback in the excitable case. More specifically, we are concerned with the generation of stable…
The Linear Threshold Model (LTM) is widely used to study the propagation of collective behaviors as complex contagions. However, its dependence on discrete states and timesteps restricts its ability to capture the multiple time-scales…
Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has…
Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these…
Dynamics of a chaotic spiking neuron model are being studied mathematically and experimentally. The Nonlinear Dynamic State neuron (NDS) is analysed to further understand the model and improve it. Chaos has many interesting properties such…
Reservoir computing (RC) is a novel approach to time series prediction using recurrent neural networks. In RC, an input signal perturbs the intrinsic dynamics of a medium called a reservoir. A readout layer is then trained to reconstruct a…
Spiking Neural Networks (SNNs) are biologically plausible models that have been identified as potentially apt for deploying energy-efficient intelligence at the edge, particularly for sequential learning tasks. However, training of SNNs…
Three-dimensional (3D) dissipative soliton existed in spatiotemporal mode-locked (STML) multimode fiber laser has been demonstrated to be a promising formalism for generating high-energy femtosecond pulses, which unfortunately exhibit…
Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model…
We characterize the operation of semiconductor microring lasers in an excitable regime. Our experiments reveal a statistical distribution of the characteristics of noise-triggered optical pulses that is not observed in other excitable…
Neural networks has been successfully used in the processing of Lidar data, especially in the scenario of autonomous driving. However, existing methods heavily rely on pre-processing of the pulse signals derived from Lidar sensors and…