Lancelot Da Costa,Tomáš Gavenčiak,David Hyland et al.
Lancelot Da Costa et al.
This paper offers a road map for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible path toward scalable aligned AI rests on enabling artificial a...
Working Memory and Self-Directed Inner Speech Enhance Multitask Generalization in Active Inference [0.03%]
工作记忆和自我指示的内心言语通过主动推理增强多任务迁移能力
Jeffrey Frederic Queißer,Jun Tani
Jeffrey Frederic Queißer
This simulation study shows how a set of working memory tasks can be acquired simultaneously through interaction between a stacked recurrent neural network (RNN) and multiple working memories. In these tasks, temporal patterns are provided,...
Christof Fehrman,C Daniel Meliza
Christof Fehrman
Neural manifolds are an attractive theoretical framework for characterizing the complex behaviors of neural populations. However, many of the tools for identifying these low-dimensional subspaces are correlational and provide limited insigh...
Taiki Yamada,Yuichi Katori,Kantaro Fujiwara
Taiki Yamada
Echo state networks (ESNs) are a class of recurrent neural networks in which only the readout layer is trainable, while the recurrent and input layers are fixed. This architectural constraint enables computationally efficient processing of ...
A Chimera Model for Motion Anticipation in the Retina and the Primary Visual Cortex [0.03%]
视网膜和初级视觉皮层中运动预测的嵌合模型
Jérôme Emonet,Selma Souihel,Frédéric Chavane et al.
Jérôme Emonet et al.
We propose a mean field model of the primary visual cortex (V1), connected to a realistic retina model, to study the impact of the retina on motion anticipation. We first consider the case where the retina does not itself provide anticipati...
Mawaba Pascal Dao,Adrian M Peter
Mawaba Pascal Dao
Active inference, grounded in the free energy principle, provides a powerful lens for understanding how agents balance exploration and goal-directed behavior in uncertain environments. Here, we propose a new planning framework that integrat...
Simon Wilshin,Matthew D Kvalheim,Clayton Scott et al.
Simon Wilshin et al.
Oscillators are ubiquitous in nature and are usually associated with the existence of an asymptotic phase that governs the long-term dynamics of the oscillator. We show that the asymptotic phase can be estimated using a carefully chosen ser...
Fusing Foveal Fixations Using Linear Retinal Transformations and Bayesian Experimental Design [0.03%]
基于贝叶斯实验设计和线性视网膜变换的融合注视点方法
Christopher K I Williams
Christopher K I Williams
Humans (and many vertebrates) face the problem of fusing together multiple fixations of a scene in order to obtain a representation of the whole, where each fixation uses a high-resolution fovea and decreasing resolution in the periphery. I...
Modeling Higher-Order Interactions in Sparse and Heavy-Tailed Neural Population Activity [0.03%]
稀疏且尾部沉重的神经元群体活动中高阶相互作用的建模
Ulises Rodríguez-Domínguez,Hideaki Shimazaki
Ulises Rodríguez-Domínguez
Neurons process sensory stimuli efficiently, showing sparse yet highly variable ensemble spiking activity involving structured higher-order interactions. Notably, while neural populations are mostly silent, they occasionally exhibit highly ...
Feature Normalization Prevents Collapse of Noncontrastive Learning Dynamics [0.03%]
特征规范化防止非对比学习动力学崩溃
Han Bao
Han Bao
Contrastive learning is a self-supervised representation learning framework where two positive views generated through data augmentation are made similar by an attraction force in a data representation space, while a repulsive force makes t...