Théophile Champion,Marek Grześ,Howard Bowman
Théophile Champion
Active inference is a state-of-the-art framework for modeling the brain that explains a wide range of mechanisms. Recently, two versions of branching time active inference (BTAI) have been developed to handle the exponential (space and time...
Trainable Reference Spikes Improve Temporal Information Processing of SNNs With Supervised Learning [0.03%]
基于监督学习的可训练参考脉冲改善SNN的时间信息处理能力
Zeyuan Wang,Luis Cruz
Zeyuan Wang
Spiking neural networks (SNNs) are the next-generation neural networks composed of biologically plausible neurons that communicate through trains of spikes. By modifying the plastic parameters of SNNs, including weights and time delays, SNN...
Active Inference and Reinforcement Learning: A Unified Inference on Continuous State and Action Spaces Under Partial Observability [0.03%]
主动推理与强化学习：部分可观测连续状态和动作空间上的统一推理框架
Parvin Malekzadeh,Konstantinos N Plataniotis
Parvin Malekzadeh
Reinforcement learning (RL) has garnered significant attention for developing decision-making agents that aim to maximize rewards, specified by an external supervisor, within fully observable environments. However, many real-world problems ...
Michał Markiewicz,Ireneusz Brzozowski,Szymon Janusz
Michał Markiewicz
Von Neumann architecture requires information to be encoded as numerical values. For that reason, artificial neural networks running on computers require the data coming from sensors to be discretized. Other network architectures that more ...
Mechanism of Duration Perception in Artificial Brains Suggests New Model of Attentional Entrainment [0.03%]
人工大脑持续时间感知机制提出注意力同步新模型
Ali Tehrani-Saleh,J Devin McAuley,Christoph Adami
Ali Tehrani-Saleh
While cognitive theory has advanced several candidate frameworks to explain attentional entrainment, the neural basis for the temporal allocation of attention is unknown. Here we present a new model of attentional entrainment guided by empi...
Martin Magris,Mostafa Shabani,Alexandros Iosifidis
Martin Magris
We propose an optimization algorithm for variational inference (VI) in complex models. Our approach relies on natural gradient updates where the variational space is a Riemann manifold. We develop an efficient algorithm for gaussian variati...
Jan Melchior,Robin Schiewer,Laurenz Wiskott
Jan Melchior
This study discusses the negative impact of the derivative of the activation functions in the output layer of artificial neural networks, in particular in continual learning. We propose Hebbian descent as a theoretical framework to overcome...
Nina Baldy,Martin Breyton,Marmaduke M Woodman et al.
Nina Baldy et al.
The process of inference on networks of spiking neurons is essential to decipher the underlying mechanisms of brain computation and function. In this study, we conduct inference on parameters and dynamics of a mean-field approximation, simp...
Top-Down Priors Disambiguate Target and Distractor Features in Simulated Covert Visual Search [0.03%]
顶端先验在模拟隐蔽视觉搜索中对目标和干扰物特征进行消除模糊性
Justin D Theiss,Michael A Silver
Justin D Theiss
Several models of visual search consider visual attention as part of a perceptual inference process, in which top-down priors disambiguate bottom-up sensory information. Many of these models have focused on gaze behavior, but there are rela...
Deconstructing Deep Active Inference: A Contrarian Information Gatherer [0.03%]
拆解深度主动推断：一个反传统的信息搜集者
Théophile Champion,Marek Grześ,Lisa Bonheme et al.
Théophile Champion et al.
Active inference is a theory of perception, learning, and decision making that can be applied to neuroscience, robotics, psychology, and machine learning. Recently, intensive research has been taking place to scale up this framework using M...